© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30772
    Prev
    Next
    INDEX
    Explanations

    addams, airport, blog, family

    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_7_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
    v
    1.99
    z
    1.74
    al
    1.73
    л
    1.69
    í
    1.66
    u
    1.61
    t
    1.60
    r
    1.56
    the
    1.55
    d
    1.55
    POSITIVE LOGITS
     to
    1.30
     not
    1.16
     you
    1.15
     in
    1.12
     an
    1.11
     в
    1.08
     be
    1.06
     into
    1.05
     by
    1.03
     diaphragm
    1.03
    Activations Density 0.000%

    No Known Activations