© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    the start of lines that are heavily indented and legal documents

    oai_token-act-pair · gemini-2.0-flash

    crime

    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
    <bos>
    -0.87
    G
    -0.46
     /\.
    -0.44
    R
    -0.44
    I
    -0.42
    S
    -0.41
    L
    -0.41
     personali
    -0.39
    Continue
    -0.39
    offsetTop
    -0.39
    POSITIVE LOGITS
    存于互联网档案馆
    0.66
    Bibliograf
    0.65
    CodeAttribute
    0.65
    ValueGenerated
    0.65
     mergeFrom
    0.64
    InjectAttribute
    0.63
     Signalez
    0.62
    ArgsConstructor
    0.62
    brainly
    0.62
    ValueStyle
    0.61
    Activations Density 7.500%

    No Known Activations