© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78979
    Prev
    Next
    INDEX
    Explanations

    rich foods

    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_0_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
    ری
    1.56
    ьте
    1.47
    ला
    1.38
    اری
    1.34
    ٹ
    1.31
    ם
    1.30
    εια
    1.27
    یاء
    1.26
    یده
    1.20
    не
    1.20
    POSITIVE LOGITS
    ي
    2.59
    i
    2.20
    an
    1.97
    ed
    1.83
    et
    1.80
    י
    1.64
    as
    1.61
    es
    1.60
     landen
    1.53
    j
    1.53
    Activations Density 0.001%

    No Known Activations