© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 840
    Prev
    Next
    INDEX
    Explanations

    python code with references to self, list properties, and storage profiles

    oai_token-act-pair · gemini-2.0-flash

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    yntaxException
    -0.70
     useState
    -0.68
    useState
    -0.65
    存于互联网档案馆
    -0.63
     HasFactory
    -0.60
    MenuInflater
    -0.59
    醐
    -0.57
    setVerticalGroup
    -0.56
     stoneware
    -0.56
    ArrowToggle
    -0.55
    POSITIVE LOGITS
    <bos>
    0.72
    jooq
    0.57
    vore
    0.57
    persky
    0.54
    OOTDTY
    0.52
    IPAddress
    0.52
    الحياه
    0.52
     يتيمه
    0.51
    ksen
    0.50
    ngdoc
    0.50
    Activations Density 7.219%

    No Known Activations