© 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. 90342
    Prev
    Next
    INDEX
    Explanations

    priestess

    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
    ता
    0.63
    و
    0.57
    та
    0.56
    ün
    0.53
    }(
    0.53
    п
    0.52
    的环境
    0.52
    skih
    0.51
    ו
    0.51
     escog
    0.50
    POSITIVE LOGITS
    ي
    0.75
    i
    0.73
    да
    0.67
    ed
    0.66
    ad
    0.64
    ๋ยว
    0.59
     paix
    0.59
    il
    0.59
    ста
    0.59
    思議
    0.59
    Activations Density 0.000%

    No Known Activations