© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201312
    Prev
    Next
    INDEX
    Explanations

    the better

    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_6_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
    u
    1.04
    I
    1.02
    a
    1.01
    া
    1.01
    ?
    1.00
    ;
    0.99
    daughters
    0.89
    ᱑
    0.86
    r
    0.84
    OpenCamera
    0.81
    POSITIVE LOGITS
    ты
    1.05
    ви
    0.98
     bomber
    0.91
    тың
    0.89
    ارى
    0.87
     buen
    0.84
    تر
    0.83
     (
    0.82
    spieler
    0.81
    ري
    0.81
    Activations Density 0.003%

    No Known Activations