© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39005
    Prev
    Next
    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    тивних
    0.43
    gli
    0.38
     tend
    0.37
    jdField
    0.37
     सार्व
    0.36
     Irland
    0.34
    "{@
    0.34
     slaughtered
    0.34
     maintains
    0.33
    蒡
    0.33
    POSITIVE LOGITS
     Monde
    0.42
    ESCO
    0.42
    Ag
    0.39
     Ag
    0.39
    Accommodation
    0.39
     Bad
    0.38
     Pó
    0.38
     Assurance
    0.38
    Ass
    0.38
     Ment
    0.38
    Activations Density 0.003%

    No Known Activations