© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7324
    Prev
    Next
    INDEX
    Explanations

    helpline numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ần
    1.15
    в
    1.04
    га
    1.02
    is
    0.97
    <td>
    0.96
     ră
    0.95
     Правда
    0.94
    ին
    0.94
    ውን
    0.93
    edited
    0.93
    POSITIVE LOGITS
     anteced
    1.29
     neutrons
    1.27
    嶇
    1.24
     контак
    1.24
    껐
    1.23
     bist
    1.21
    วน
    1.21
    રિક
    1.18
     axons
    1.16
     بشأن
    1.14
    Activations Density 0.112%

    No Known Activations