© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    sections of code or text that are heavily indented, potentially indicating the start of a new code block or section

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific information

    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
    <bos>
    -1.85
     itſelf
    -1.06
     houſe
    -1.05
     myſelf
    -1.02
     himſelf
    -0.98
     Monfieur
    -0.96
     purpoſe
    -0.96
     themſelves
    -0.93
     faſt
    -0.91
     Reſ
    -0.91
    POSITIVE LOGITS
     REASON
    0.47
    ritic
    0.46
    liac
    0.44
     ar
    0.44
     fo
    0.43
    IMPORTED
    0.42
    WALK
    0.41
    perg
    0.41
     aus
    0.41
     EventArgs
    0.41
    Activations Density 0.343%

    No Known Activations