© 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. 13229
    Prev
    Next
    INDEX
    Explanations

    short, common words, especially articles and pronouns, sometimes near words describing experience

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or code syntax

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

    a

    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
    ÓS
    -0.49
    inton
    -0.48
    uri
    -0.47
     Fores
    -0.46
     HttpHeaders
    -0.46
    ularis
    -0.45
    āju
    -0.45
    my
    -0.44
     liné
    -0.44
     mechanism
    -0.44
    POSITIVE LOGITS
    ReusableCell
    0.76
    +#+#
    0.75
    IsContent
    0.75
     समीक्षाओं
    0.71
    UnusedPrivate
    0.70
    Havolalar
    0.64
     CreateTagHelper
    0.63
    LEncoder
    0.63
    __*/
    0.62
    GOTREF
    0.61
    Activations Density 1.019%

    No Known Activations