© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199633
    Prev
    Next
    INDEX
    Explanations

    137

    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_12_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
    Enable
    0.48
     परेशानी
    0.48
    (
    0.47
     ->
    0.47
     हैव
    0.47
    Liens
    0.47
     wint
    0.46
     พ
    0.46
     タ
    0.46
     आइडेंट
    0.45
    POSITIVE LOGITS
     límites
    0.55
     berbicara
    0.52
    хі
    0.49
     q
    0.49
     trái
    0.48
     maîtres
    0.48
     murdered
    0.47
     क़
    0.47
    ється
    0.47
    yszer
    0.47
    Activations Density 0.000%

    No Known Activations