© 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. 46673
    Prev
    Next
    INDEX
    Explanations

    medicine and law institutions

    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
     godine
    0.82
     уви
    0.82
     powied
    0.78
    )、
    0.73
    জ
    0.71
    ä
    0.70
    чи
    0.70
     času
    0.70
    는
    0.69
     ви
    0.68
    POSITIVE LOGITS
    kite
    0.85
    t
    0.84
    kis
    0.80
    keto
    0.74
    kala
    0.72
    kin
    0.70
    kör
    0.70
    kana
    0.69
    kita
    0.69
    kota
    0.68
    Activations Density 0.000%

    No Known Activations