© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193344
    Prev
    Next
    INDEX
    Explanations

    satisfait / unsat (satisfaction/unsatisfaction)

    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_4_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
    '
    1.23
    ي
    1.21
    y
    1.00
    e
    0.98
    <0x80>
    0.93
    i
    0.93
    s
    0.91
    ع
    0.91
    k
    0.85
    kA
    0.84
    POSITIVE LOGITS
    1
    1.11
     a
    1.08
     as
    0.98
    5
    0.89
    lis
    0.84
    list
    0.83
    ip
    0.80
    does
    0.77
    8
    0.75
    lot
    0.74
    Activations Density 0.002%

    No Known Activations