© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58132
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     -
    0.57
    +
    0.50
    ?
    0.46
    Gross
    0.41
    dozen
    0.41
    −</
    0.40
    unsubscribe
    0.39
    ??
    0.39
    ци
    0.39
    Restaurant
    0.39
    POSITIVE LOGITS
     MOM
    0.59
     mom
    0.54
     ess
    0.54
     mum
    0.53
     hl
    0.48
     ca
    0.47
     rr
    0.46
     MUM
    0.46
     mikro
    0.46
    )--(
    0.46
    Activations Density 0.000%

    No Known Activations