© 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. 7651
    Prev
    Next
    INDEX
    Explanations

    quickly followed by actions

    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
    ر
    1.31
     thưởng
    1.02
    \%
    1.02
    ५
    0.99
    𝚛
    0.96
    Zobacz
    0.94
    ১
    0.94
     Tuttavia
    0.93
    гор
    0.91
    력
    0.91
    POSITIVE LOGITS
    en
    1.14
    }^{*}
    1.09
    ^[
    1.02
    檚
    1.00
    要去
    0.99
    nian
    0.94
     eluted
    0.93
    amiento
    0.93
    nancy
    0.92
     adsorbed
    0.91
    Activations Density 0.018%

    No Known Activations