© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112960
    Prev
    Next
    INDEX
    Explanations

    Habanero

    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_2_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
    し
    1.13
    on
    1.09
    𝙥
    1.04
    وم
    0.95
    jší
    0.91
    aría
    0.85
    arı
    0.85
    𝙖
    0.83
    𝙨
    0.81
    ()=>{
    0.80
    POSITIVE LOGITS
    -
    1.31
    ン
    0.94
    น
    0.93
    सी
    0.84
    н
    0.82
    ة
    0.80
    —
    0.76
    IL
    0.75
     tenter
    0.75
     that
    0.74
    Activations Density 0.000%

    No Known Activations