© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15719
    Prev
    Next
    INDEX
    Explanations

    the word "such", sometimes with an additional weak signal for nearby numbers and comparatives

    oai_token-act-pair · gemini-2.0-flash

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -1.04
    <bos>
    -0.80
    '
    -0.80
    ↵
    -0.79
    <eos>
    -0.76
    ’
    -0.66
     of
    -0.59
     and
    -0.57
     had
    -0.56
    ‘
    -0.54
    POSITIVE LOGITS
    InputBorder
    1.22
    RenderAtEndOf
    1.16
    bootstrapcdn
    1.04
    IntoConstraints
    1.03
    mybatisplus
    0.98
     MainAxisSize
    0.97
    ChildScrollView
    0.96
    ArgsConstructor
    0.96
    ."</
    0.96
    newswire
    0.95
    Activations Density 0.846%

    No Known Activations