© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50001
    Prev
    Next
    INDEX
    Explanations

    What

    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_55_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
    पा
    0.44
     tratando
    0.39
     नि
    0.37
    sinatra
    0.37
     harmful
    0.36
    獾
    0.36
     meant
    0.36
     помощи
    0.36
    꿇
    0.36
    ड़ा
    0.34
    POSITIVE LOGITS
    allowSlide
    0.42
     nevo
    0.42
     Svet
    0.41
    Ľ
    0.41
     even
    0.40
     convexes
    0.40
    even
    0.40
     CallOptions
    0.38
    šev
    0.38
     bahkan
    0.37
    Activations Density 0.008%

    No Known Activations