© 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. 127088
    Prev
    Next
    INDEX
    Explanations

    treasury, manager, government, laws

    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
    .
    0.60
    0.58
    ﱢ
    0.58
     governo
    0.57
     strategie
    0.55
     malicious
    0.54
     nmea
    0.53
    ૦
    0.53
    ೦
    0.53
     Governo
    0.53
    POSITIVE LOGITS
    و
    0.82
    för
    0.73
    на
    0.70
    า
    0.68
    다
    0.68
    s
    0.67
    für
    0.64
    5
    0.63
    fatal
    0.59
    ної
    0.59
    Activations Density 0.016%

    No Known Activations