© 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. 91611
    Prev
    Next
    INDEX
    Explanations

    sequencing numbers 7

    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
    ,
    0.83
    কে
    0.79
    א
    0.78
    る
    0.78
    ли
    0.74
    اً
    0.74
     has
    0.73
    的女
    0.73
    تين
    0.73
    라는
    0.71
    POSITIVE LOGITS
    ↵↵
    0.88
    ס
    0.81
    hy
    0.75
    hit
    0.75
    hug
    0.71
    h
    0.70
    ర్
    0.67
    hm
    0.66
     Abilities
    0.66
    ↵
    0.64
    Activations Density 0.016%

    No Known Activations