© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193984
    Prev
    Next
    INDEX
    Explanations

    2nd Gen

    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_4_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
    ق
    1.07
    дят
    0.97
    in
    0.96
    д
    0.95
     adjoining
    0.93
    oc
    0.93
    τε
    0.90
    adaki
    0.88
    is
    0.87
     autrement
    0.85
    POSITIVE LOGITS
    r
    1.08
    。
    1.08
     been
    0.95
    ។
    0.93
    ।
    0.92
    s
    0.89
    ిన
    0.88
    I
    0.86
     in
    0.84
    a
    0.82
    Activations Density 0.002%

    No Known Activations