© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10301
    Prev
    Next
    INDEX
    Explanations

    numerical data and units

    oai_token-act-pair · gemini-2.0-flash

    statistics with numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ^(@)
    -0.97
     myſelf
    -0.97
     Monfieur
    -0.95
     Efq
    -0.93
     $_"
    -0.88
     itſelf
    -0.87
     poffible
    -0.85
     Shakspeare
    -0.83
     Theſe
    -0.81
     ―――――
    -0.77
    POSITIVE LOGITS
     &
    0.80
     /
    0.76
    </td>
    0.74
    ot
    0.74
     and
    0.73
    </b>
    0.71
    ov
    0.71
    5
    0.71
    .
    0.71
    </sup>
    0.70
    Activations Density 56.375%

    No Known Activations