© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89475
    Prev
    Next
    INDEX
    Explanations

    Schulz, Dunbar, Biden, Alcohol

    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_3_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
    ll
    0.82
    ne
    0.74
     I
    0.73
    da
    0.73
    ية
    0.73
    리
    0.73
    на
    0.71
    ट
    0.70
    iv
    0.70
    ng
    0.69
    POSITIVE LOGITS
     необходи
    0.68
     раствора
    0.68
    ками
    0.66
    <0x0E>
    0.63
     базу
    0.63
    انى
    0.63
    اني
    0.63
     کوډ
    0.63
     jedną
    0.63
     важ
    0.62
    Activations Density 0.000%

    No Known Activations