© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233617
    Prev
    Next
    INDEX
    Explanations

    acceptance and rejection

    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
     hand
    0.83
    手
    0.68
    hand
    0.64
     Hand
    0.64
    Hand
    0.62
     HAND
    0.59
    손
    0.55
     mão
    0.55
    HAND
    0.55
     손
    0.53
    POSITIVE LOGITS
    Notes
    0.41
    mete
    0.39
    hai
    0.39
    notes
    0.38
    ផុត
    0.38
     considerar
    0.36
    deprecated
    0.36
    Oi
    0.35
    Rus
    0.35
     নোট
    0.34
    Activations Density 0.025%

    No Known Activations