© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17582
    Prev
    Next
    INDEX
    Explanations

    new Scanner

    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_40_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
    )").
    0.43
    }`));
    0.37
     використо
    0.37
    )$;
    0.37
     marchand
    0.37
    Union
    0.37
     simplifié
    0.36
     \%)$
    0.36
    垩
    0.35
     รอ
    0.35
    POSITIVE LOGITS
    toDouble
    0.40
     Pick
    0.38
     Sight
    0.38
    pik
    0.38
     स्कैनर
    0.37
    пру
    0.37
    rouge
    0.37
    紧
    0.37
    Sight
    0.37
     Scanner
    0.36
    Activations Density 0.000%

    No Known Activations