© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58074
    Prev
    Next
    INDEX
    Explanations

    every other

    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_2_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
    to
    1.81
    ى
    1.78
    il
    1.66
    то
    1.63
    in
    1.60
    ą
    1.55
    the
    1.48
    t
    1.45
    า
    1.41
    r
    1.39
    POSITIVE LOGITS
    ம்
    1.07
    嚧
    0.92
    กอง
    0.90
    只好
    0.89
    dött
    0.88
    乸
    0.88
    }+\
    0.87
    kka
    0.87
     voila
    0.87
    م
    0.87
    Activations Density 0.000%

    No Known Activations