© 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. 90784
    Prev
    Next
    INDEX
    Explanations

    SQL injection, cafe, program

    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
    al
    0.72
    sun
    0.70
    u
    0.69
    h
    0.67
    ش
    0.66
    st
    0.63
    ra
    0.63
     -\
    0.62
    ls
    0.61
    ?\
    0.61
    POSITIVE LOGITS
    ון
    0.72
     celebró
    0.72
    '
    0.67
    ají
    0.64
    う
    0.64
    iamo
    0.63
    året
    0.63
     tackling
    0.63
    čio
    0.63
    ണ
    0.62
    Activations Density 0.003%

    No Known Activations