© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177128
    Prev
    Next
    INDEX
    Explanations

    SAM

    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_50_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
    注明
    0.39
    डेट
    0.39
    kf
    0.37
     Keywords
    0.37
    즈
    0.37
    桌
    0.36
    킨
    0.36
    ార
    0.35
     Drawings
    0.35
    毫
    0.35
    POSITIVE LOGITS
    াদেশিক
    0.43
    ട്ര
    0.42
    Ronald
    0.42
     Ignatius
    0.42
     fresco
    0.40
    andre
    0.40
    ASD
    0.39
    radle
    0.39
    ocaps
    0.39
     collett
    0.39
    Activations Density 0.001%

    No Known Activations