© 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. 205964
    Prev
    Next
    INDEX
    Explanations

    full

    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
     ON
    1.26
     On
    1.13
    ON
    1.09
    オン
    1.03
    On
    1.01
     온
    0.97
    온
    0.97
     ऑन
    0.93
    ऑन
    0.87
     onwards
    0.82
    POSITIVE LOGITS
    planning
    0.38
     surfaced
    0.35
    纯
    0.35
     roca
    0.35
    んで
    0.34
    ар
    0.34
    {{
    0.34
    gü
    0.34
     ste
    0.34
     ups
    0.33
    Activations Density 0.005%

    No Known Activations