© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42325
    Prev
    Next
    INDEX
    Explanations

    dead code elimination

    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_3_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
    I
    0.88
    IN
    0.77
    in
    0.73
    IIT
    0.68
    서
    0.68
    ate
    0.67
    Body
    0.66
    Cursor
    0.66
    r
    0.66
    ations
    0.64
    POSITIVE LOGITS
     ו
    0.89
     и
    0.84
     идеа
    0.84
     في
    0.82
     σε
    0.81
     ότι
    0.80
     و
    0.79
     instr
    0.77
     ও
    0.75
     в
    0.74
    Activations Density 0.001%

    No Known Activations