© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39177
    Prev
    Next
    INDEX
    Explanations

    overemphasis on, overactive

    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
    ி
    0.82
    ی
    0.80
    ও
    0.73
    ৫
    0.70
    古墳
    0.70
     می‌توان
    0.69
     recentemente
    0.69
    એ
    0.69
     ponctués
    0.69
    ১
    0.68
    POSITIVE LOGITS
     by
    1.14
    1.07
     at
    0.82
    at
    0.82
     for
    0.80
    v
    0.72
    rg
    0.68
    ей
    0.67
     aliquot
    0.67
    ud
    0.66
    Activations Density 0.018%

    No Known Activations