© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136725
    Prev
    Next
    INDEX
    Explanations

    creating web pages

    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_12_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
     сдела
    0.55
    ാല
    0.53
     botanical
    0.53
     скон
    0.53
     сказа
    0.52
    守
    0.52
    数十
    0.51
     запре
    0.51
    liny
    0.51
     timid
    0.50
    POSITIVE LOGITS
    گ
    0.59
    Câu
    0.56
    Hrs
    0.56
     EDUCATION
    0.55
    jaar
    0.55
    Bună
    0.54
    ت
    0.54
    پ
    0.52
    Н
    0.52
    ভারত
    0.52
    Activations Density 0.001%

    No Known Activations