© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10283
    Prev
    Next
    INDEX
    Explanations

    isolated single letter tokens, especially those commonly used as variables in mathematical expressions, along with any number that begins with `1`

    oai_token-act-pair · gemini-2.0-flash

    symbols or terms likely related to mathematical or programming functions

    np_token-act-pair-logits · gpt-4o-mini

    variable x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الدراسه
    -0.65
    IsContent
    -0.63
    पया
    -0.57
    zule
    -0.56
    protoimpl
    -0.56
    moveToFirst
    -0.56
    úgó
    -0.54
     brazo
    -0.53
    getDescriptor
    -0.52
     antemano
    -0.52
    POSITIVE LOGITS
    AxisAlignment
    0.56
     disambiguazione
    0.52
    ⓘ
    0.50
     Mandi
    0.49
    setViewName
    0.47
    ưởng
    0.47
    #+#
    0.46
    าย
    0.45
    ientí
    0.45
    cdr
    0.44
    Activations Density 5.824%

    No Known Activations