© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39073
    Prev
    Next
    INDEX
    Explanations

    check if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    credibly
    0.68
    Please
    0.61
    Char
    0.60
    Vincent
    0.58
    A
    0.58
    By
    0.57
    Okay
    0.57
    among
    0.57
    audience
    0.57
    ล
    0.57
    POSITIVE LOGITS
    り
    0.84
    с
    0.71
    ш
    0.70
     marginalized
    0.70
    ма
    0.69
     в
    0.68
    ան
    0.68
     in
    0.66
     tourisme
    0.65
    áním
    0.65
    Activations Density 0.004%

    No Known Activations