© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211128
    Prev
    Next
    INDEX
    Explanations

    fornication, farmer, group, niceness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    t
    1.39
    <h2>
    1.21
    <h3>
    1.16
     of
    1.13
    l
    1.13
    ン
    1.09
    ll
    1.07
    る
    1.07
     ന
    1.02
    a
    1.02
    POSITIVE LOGITS
    ва
    1.36
    ור
    1.14
    이면
    1.05
    рии
    1.03
    った
    1.00
    ры
    0.99
    kenalkan
    0.99
    вает
    0.97
     mezzanine
    0.93
     banning
    0.92
    Activations Density 0.000%

    No Known Activations