© 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. 58068
    Prev
    Next
    INDEX
    Explanations

    chalk sticks

    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
     I
    1.53
    _
    1.34
    r
    0.98
    ali
    0.95
     was
    0.93
    .’
    0.92
    ne
    0.91
    ll
    0.91
    UM
    0.90
    ara
    0.89
    POSITIVE LOGITS
    ना
    1.66
    ла
    1.55
    to
    1.35
    다
    1.34
    ע
    1.30
    יש
    1.29
    ad
    1.28
    ма
    1.28
    ю
    1.25
    ح
    1.24
    Activations Density 0.000%

    No Known Activations