© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134472
    Prev
    Next
    INDEX
    Explanations

    hashtags and special characters

    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_37_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
    ツイ
    0.45
    jab
    0.40
    原创
    0.40
    クリ
    0.39
    입
    0.39
    ناب
    0.39
    贾
    0.39
    ấn
    0.38
    符合
    0.37
    లేదు
    0.37
    POSITIVE LOGITS
     negligence
    0.41
     dad
    0.41
     medit
    0.41
     Rat
    0.40
    幹線
    0.40
    STEN
    0.39
     guiding
    0.39
     subtitle
    0.38
     protective
    0.38
    δη
    0.38
    Activations Density 0.003%

    No Known Activations