© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199088
    Prev
    Next
    INDEX
    Explanations

    design followed by suffixes (e.g., ated, ation)

    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
    AJ
    0.75
     Linie
    0.71
    ot
    0.70
     .
    0.70
     Sumatra
    0.70
     Estou
    0.69
    AS
    0.68
    ES
    0.68
    า
    0.67
    ua
    0.66
    POSITIVE LOGITS
    ，
    0.77
    ال
    0.71
    ных
    0.68
    ↵
    0.67
    the
    0.67
    time
    0.63
     relevance
    0.63
    き
    0.63
    enced
    0.62
     kinetics
    0.62
    Activations Density 0.000%

    No Known Activations