© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138199
    Prev
    Next
    INDEX
    Explanations

    provisions of law

    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_12_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
    ado
    0.69
    ade
    0.63
    veld
    0.56
    date
    0.54
    d
    0.53
    h
    0.53
    s
    0.52
    </em>
    0.49
    water
    0.49
    aho
    0.48
    POSITIVE LOGITS
    ل
    0.68
    ล
    0.65
    ল
    0.60
    mêmes
    0.57
    ल
    0.57
    ാലി
    0.55
    िल्स
    0.55
    ㇁
    0.55
     larynx
    0.55
     драмати
    0.54
    Activations Density 0.000%

    No Known Activations