© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1436
    Prev
    Next
    INDEX
    Explanations

    periods and punctuation marks, especially followed by numbers and parentheses

    oai_token-act-pair · gemini-2.0-flash

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    .
    -0.66
    .,
    -0.46
    hoe
    -0.46
     đóng
    -0.43
     behö
    -0.43
    descending
    -0.42
     getInstance
    -0.42
    市镇
    -0.42
    воря
    -0.41
    omotor
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.91
    ChildScrollView
    0.82
     виправивши
    0.81
    TagMode
    0.78
    complexContent
    0.76
     <<<<<<<<<<<<<<
    0.71
    AnimationsModule
    0.68
    UserScript
    0.67
     disambiguazione
    0.67
    SequentialGroup
    0.64
    Activations Density 2.724%

    No Known Activations