© 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. 39118
    Prev
    Next
    INDEX
    Explanations

    `chrome`, `usercontent` URLs

    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
    the
    0.96
    ta
    0.87
    س
    0.85
    ра
    0.74
    sk
    0.73
    h
    0.73
    ts
    0.70
    selt
    0.70
    f
    0.69
    sa
    0.67
    POSITIVE LOGITS
     maliciously
    0.71
     starved
    0.71
    ،
    0.71
     for
    0.70
    ৮
    0.63
     defenses
    0.61
    ৯
    0.61
    توى
    0.60
     boils
    0.59
     دليل
    0.58
    Activations Density 0.005%

    No Known Activations