© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38764
    Prev
    Next
    INDEX
    Explanations

    audio or video stream

    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_11_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
     inclu
    0.63
    amata
    0.57
    डिशा
    0.57
    𝗴
    0.56
    something
    0.55
     },
    0.55
    ்டோ
    0.55
     etwas
    0.54
     Equals
    0.54
     비슷한
    0.54
    POSITIVE LOGITS
     و
    0.53
    сом
    0.49
    ﺖ
    0.47
    kten
    0.47
     pawn
    0.46
    жи
    0.46
    ً
    0.46
    án
    0.44
     sağlam
    0.44
    k
    0.44
    Activations Density 0.003%

    No Known Activations