© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204498
    Prev
    Next
    INDEX
    Explanations

    multilingual punctuation

    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_6_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
    ו
    1.20
    و
    1.07
     in
    1.03
    <bos>
    0.86
     on
    0.84
    <0x98>
    0.81
    سى
    0.79
    но
    0.79
    td
    0.78
     giết
    0.76
    POSITIVE LOGITS
    is
    1.48
    in
    1.22
    ’
    1.22
    us
    1.02
    és
    0.98
    ot
    0.95
    ävä
    0.95
    inä
    0.95
    inin
    0.94
     traités
    0.94
    Activations Density 0.000%

    No Known Activations