© 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. 194184
    Prev
    Next
    INDEX
    Explanations

    rare terms

    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
     გამოყენ
    0.51
    ри
    0.48
     கடன்
    0.47
     каждый
    0.46
    asson
    0.46
    \
    0.46
    ан
    0.46
    том
    0.46
     كل
    0.45
    鹊
    0.45
    POSITIVE LOGITS
     microsomal
    0.49
    ]')
    0.48
    ]');
    0.48
    व्य
    0.46
     LA
    0.46
     लाह
    0.45
    ;');
    0.45
     secreted
    0.44
    也不是
    0.44
     address
    0.43
    Activations Density 0.000%

    No Known Activations