© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199529
    Prev
    Next
    INDEX
    Explanations

    careful

    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_9_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
    ли
    0.27
    ‌ای
    0.24
    ल
    0.22
    نی
    0.22
    t
    0.21
    ﺭ
    0.21
    क
    0.20
    یا
    0.20
    نیا
    0.20
    ために
    0.19
    POSITIVE LOGITS
    ol
    0.24
    بي
    0.20
    '};
    0.20
    ade
    0.20
    ED
    0.20
    បែប
    0.20
    ма
    0.19
    来说
    0.18
    其他
    0.18
    ab
    0.18
    Activations Density 0.007%

    No Known Activations