© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209306
    Prev
    Next
    INDEX
    Explanations

    numbers followed by letters or symbols

    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_25_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
     Vil
    0.42
    能力
    0.39
     foundry
    0.39
     commodities
    0.38
     impon
    0.37
     minerals
    0.37
     土
    0.37
     imports
    0.36
    vil
    0.35
     bra
    0.35
    POSITIVE LOGITS
     ≠
    0.43
    ogonal
    0.41
    ool
    0.41
     оригіналу
    0.40
     jede
    0.39
    Кто
    0.39
    ŧ
    0.39
    ῴ
    0.38
    چھ
    0.37
    કની
    0.37
    Activations Density 0.000%

    No Known Activations