© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46765
    Prev
    Next
    INDEX
    Explanations

    ak, al, ak, ak, AL, ak, ak, aker, in, in

    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_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
    d
    0.98
     ባለ
    0.82
     የመጀመሪያ
    0.81
     seagulls
    0.81
    jera
    0.80
    ắc
    0.79
    feng
    0.78
    b
    0.78
     ምስ
    0.77
    dgs
    0.77
    POSITIVE LOGITS
    in
    1.64
    या
    1.02
    ם
    0.94
    ת
    0.94
    as
    0.92
    such
    0.91
    u
    0.90
    is
    0.89
    다
    0.89
    ی
    0.88
    Activations Density 0.000%

    No Known Activations