© 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. 31084
    Prev
    Next
    INDEX
    Explanations

    principles of

    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
     odors
    0.89
     aids
    0.81
     aliments
    0.79
     cereals
    0.78
     buns
    0.77
     mice
    0.77
     bodice
    0.76
    是
    0.75
     anem
    0.73
     arsen
    0.73
    POSITIVE LOGITS
    t
    1.31
    us
    1.16
    en
    1.16
    ul
    1.15
    er
    1.08
    ong
    1.08
    an
    1.05
    ou
    1.05
    aj
    1.05
    id
    1.03
    Activations Density 0.020%

    No Known Activations