© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24772
    Prev
    Next
    INDEX
    Explanations

    remainders

    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_10_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
    F
    0.97
    sa
    0.81
    te
    0.80
    lo
    0.79
    sample
    0.78
    A
    0.78
    G
    0.77
    Point
    0.77
    CS
    0.75
    saldo
    0.75
    POSITIVE LOGITS
     avaient
    0.79
    اہم
    0.66
    グ
    0.66
    ك
    0.64
     nouveau
    0.63
     povos
    0.62
     compartilh
    0.61
     meiosis
    0.60
     б
    0.59
    ,<
    0.59
    Activations Density 0.000%

    No Known Activations