© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199790
    Prev
    Next
    INDEX
    Explanations

    by associated with source/creator

    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_12_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
     রহমানকে
    0.53
     родо
    0.51
    Fri
    0.51
     ڕۆ
    0.50
    ша
    0.50
    be
    0.49
    🍤
    0.48
    на
    0.48
    ಂ
    0.48
    롭
    0.48
    POSITIVE LOGITS
     der
    0.75
    ed
    0.61
     oleh
    0.60
    يهم
    0.60
     by
    0.59
    ickt
    0.59
     The
    0.58
    es
    0.57
    artikel
    0.57
    íř
    0.57
    Activations Density 0.001%

    No Known Activations