© 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. 161995
    Prev
    Next
    INDEX
    Explanations

    already done

    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
    ,
    1.16
     مختلف
    0.87
    ,【
    0.80
     gezegd
    0.80
    zaam
    0.79
     şekilde
    0.77
     зарабаты
    0.76
    )}$,
    0.75
    стта
    0.75
    ²,
    0.74
    POSITIVE LOGITS
    in
    1.90
    is
    1.84
    s
    1.81
    c
    1.66
    to
    1.59
    ال
    1.59
    l
    1.58
    can
    1.55
    p
    1.50
    ب
    1.48
    Activations Density 0.000%

    No Known Activations