© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3980
    Prev
    Next
    INDEX
    Explanations

    the beginning of quotes

    oai_token-act-pair · gemini-2.0-flash

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    :+:
    -0.77
    ArgsConstructor
    -0.77
    AutoresizingMask
    -0.76
     []:
    -0.70
    +#+
    -0.70
    rentices
    -0.69
     absten
    -0.68
    hdashline
    -0.68
     مشين
    -0.66
    fromnode
    -0.66
    POSITIVE LOGITS
    <bos>
    2.45
    The
    0.67
    I
    0.66
     the
    0.62
    '
    0.59
    B
    0.58
    ↵
    0.57
     The
    0.55
    E
    0.53
    P
    0.52
    Activations Density 1.515%

    No Known Activations