© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158013
    Prev
    Next
    INDEX
    Explanations

    hoi an, hoi4

    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_2_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
     යන
    1.09
     ١
    0.97
    ز
    0.96
    ní
    0.95
     a
    0.94
    ኋላ
    0.93
    ция
    0.92
    IRE
    0.91
    ६
    0.89
    onavírus
    0.89
    POSITIVE LOGITS
    "
    1.77
    س
    1.63
    ن
    1.47
    '
    1.32
     for
    1.28
    ل
    1.27
    ু
    1.20
    ra
    1.20
    <h2>
    1.12
    s
    1.11
    Activations Density 0.000%

    No Known Activations