© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90274
    Prev
    Next
    INDEX
    Explanations

    say "{"

    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_60_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
    K
    0.77
    G
    0.73
     t
    0.68
    F
    0.67
    U
    0.67
    Bs
    0.66
    O
    0.65
    Or
    0.64
    N
    0.64
    But
    0.64
    POSITIVE LOGITS
    cl
    0.65
    che
    0.63
    me
    0.63
    fr
    0.62
    je
    0.62
    f
    0.62
    vir
    0.61
    d
    0.61
    cook
    0.61
    feb
    0.61
    Activations Density 0.000%

    No Known Activations