© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130519
    Prev
    Next
    INDEX
    Explanations

    Indian languages and traditions

    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_1_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
    l
    1.03
    2
    1.03
    t
    1.01
    1
    1.01
    <0x80>
    0.93
    that
    0.84
    directed
    0.78
    r
    0.77
    district
    0.77
    dale
    0.75
    POSITIVE LOGITS
    ä
    1.17
    :
    1.02
    ou
    0.80
    iv
    0.79
    ın
    0.79
    ing
    0.79
    ovania
    0.78
     shreds
    0.78
    un
    0.77
     panes
    0.74
    Activations Density 0.002%

    No Known Activations