© 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. 42181
    Prev
    Next
    INDEX
    Explanations

    port scan, forward, scan

    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
    '
    1.09
    t
    0.93
    a
    0.93
    p
    0.92
    ا
    0.89
    و
    0.84
    y
    0.84
    n
    0.83
    g
    0.77
    liği
    0.72
    POSITIVE LOGITS
    $}
    0.59
     roku
    0.59
     samma
    0.59
     подобных
    0.58
     portraits
    0.57
     pudd
    0.57
    㢄
    0.57
     musicales
    0.56
    elevationMap
    0.56
     oficio
    0.56
    Activations Density 0.006%

    No Known Activations