© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204618
    Prev
    Next
    INDEX
    Explanations

    H

    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_56_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
    льнявыя
    0.34
    ctors
    0.33
    ünde
    0.33
     biliary
    0.33
    chit
    0.32
    {}'.
    0.32
    Exports
    0.31
     EXEMPLARY
    0.31
    ycling
    0.31
    гистра
    0.31
    POSITIVE LOGITS
     ге
    0.58
     Ге
    0.57
     Ge
    0.52
    Ге
    0.51
     ge
    0.44
    H
    0.41
    Ge
    0.41
     Gé
    0.40
    ге
    0.40
     Hé
    0.39
    Activations Density 0.000%

    No Known Activations