© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141969
    Prev
    Next
    INDEX
    Explanations

    pain in the ass

    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_0_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
    s
    1.90
    the
    1.88
    ת
    1.83
    e
    1.82
    as
    1.81
    y
    1.79
    at
    1.73
    ing
    1.70
    ir
    1.65
    are
    1.64
    POSITIVE LOGITS
     I
    1.44
    ление
    1.36
    jší
    1.25
     مؤرشف
    1.14
    "
    1.13
    д
    1.10
     ৫
    1.08
     unbear
    1.07
     STATE
    1.05
     agréable
    1.04
    Activations Density 0.000%

    No Known Activations