© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235539
    Prev
    Next
    INDEX
    Explanations

    I

    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_46_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
    льм
    0.38
    谜
    0.38
     necessari
    0.37
    ่วน
    0.37
     timely
    0.37
     replenished
    0.37
    হার
    0.36
    ==",
    0.36
    thione
    0.35
     over
    0.35
    POSITIVE LOGITS
     versucht
    0.40
    Conflict
    0.40
    Trying
    0.39
    Acting
    0.39
     AssertionError
    0.39
    ExceptionHandler
    0.39
     pokuš
    0.38
     попы
    0.38
    Ada
    0.38
     Attempt
    0.38
    Activations Density 0.000%

    No Known Activations