© 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. 63831
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Representation
    0.43
    ValueError
    0.39
     representation
    0.38
     कॉलोनी
    0.37
     решения
    0.37
     Representations
    0.37
    鲶
    0.37
    argon
    0.37
     danam
    0.36
     rang
    0.36
    POSITIVE LOGITS
     change
    0.52
     Change
    0.50
     cambiamenti
    0.47
    change
    0.46
    Change
    0.46
     prevent
    0.41
    ophyll
    0.39
     CHANGE
    0.39
     cambio
    0.39
    ⑸
    0.39
    Activations Density 0.000%

    No Known Activations