© 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. 45943
    Prev
    Next
    INDEX
    Explanations

    omens

    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
     SRAM
    0.73
    ઓ
    0.72
    醎
    0.70
     Syk
    0.69
     Jeep
    0.65
     AMOLED
    0.65
     impec
    0.65
    avion
    0.64
     tachy
    0.64
     Jackpot
    0.64
    POSITIVE LOGITS
    at
    0.93
    <0x80>
    0.92
    you
    0.83
    z
    0.81
    {
    0.80
    be
    0.73
    bl
    0.73
    വ
    0.73
    ;
    0.72
    U
    0.71
    Activations Density 0.001%

    No Known Activations