© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145162
    Prev
    Next
    INDEX
    Explanations

    sh prefixes

    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_0_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
    t
    2.00
    te
    1.73
    tól
    1.64
    ي
    1.63
    ti
    1.52
    tı
    1.52
    től
    1.52
    tl
    1.41
    dh
    1.41
    ts
    1.40
    POSITIVE LOGITS
    on
    1.66
     one
    1.59
     marijuana
    1.42
    は
    1.41
     an
    1.41
     in
    1.30
     cannabis
    1.29
     boreal
    1.25
     یکی
    1.23
     romper
    1.23
    Activations Density 0.010%

    No Known Activations