© 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. 13581
    Prev
    Next
    INDEX
    Explanations

    objective C code

    oai_token-act-pair · gemini-2.0-flash

    technical programming keywords

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

    Objective-C code

    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
     Elizabethan
    -0.57
     burials
    -0.56
     apricot
    -0.55
     Llew
    -0.54
     violets
    -0.54
     Mep
    -0.53
     fratelli
    -0.53
     grà
    -0.53
     traitors
    -0.52
     mCurrent
    -0.52
    POSITIVE LOGITS
    PyExc
    0.72
     חיצוניים
    0.65
     متعلقه
    0.59
     Normdatei
    0.59
    __;
    0.58
    UAGES
    0.57
    SerializedSize
    0.57
    awaiter
    0.57
     pinulongan
    0.57
    WriteTagHelper
    0.56
    Activations Density 2.806%

    No Known Activations