© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11491
    Prev
    Next
    INDEX
    Explanations

    the syntax of code or markup languages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    󠁢
    -0.73
     super
    -0.56
     Used
    -0.53
    gebob
    -0.50
    velle
    -0.48
    htë
    -0.48
    ContextHolder
    -0.47
     SUPER
    -0.47
    Used
    -0.46
    HtmlAttribute
    -0.46
    POSITIVE LOGITS
    Източници
    0.61
    contentLoaded
    0.59
     ProtoMessage
    0.59
    Bioaccumulative
    0.54
    adpleegd
    0.48
    LikeLike
    0.47
    IsUnicode
    0.47
    Архівовано
    0.46
    wiąz
    0.46
    ngdoc
    0.45
    Activations Density 1.922%

    No Known Activations