© 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. 204135
    Prev
    Next
    INDEX
    Explanations

    file paths and code snippets

    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
    대
    0.35
     Easter
    0.34
    ಿಸುತ್ತಾರೆ
    0.33
     Code
    0.32
     Neut
    0.32
     Prima
    0.32
     Dro
    0.31
     Producers
    0.31
     Degrees
    0.31
     Serious
    0.31
    POSITIVE LOGITS
    ⵜ
    0.37
     presencia
    0.32
    Etudes
    0.32
     ат
    0.32
    ρι
    0.32
     contenidos
    0.32
     entidad
    0.32
     contenu
    0.32
    GroupID
    0.31
     fortr
    0.31
    Activations Density 0.000%

    No Known Activations