© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215449
    Prev
    Next
    INDEX
    Explanations

    tension

    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_5_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
    \
    1.01
    ש
    1.00
    ם
    0.98
    1
    0.98
    在
    0.97
    数
    0.97
    '
    0.95
    ن
    0.95
    ON
    0.94
    ння
    0.93
    POSITIVE LOGITS
    ों
    1.09
    ।
    1.06
    g
    1.03
    pengaruhi
    0.95
    एस
    0.90
    bout
    0.89
     ajustes
    0.88
     texted
    0.88
     adopters
    0.87
     atletas
    0.86
    Activations Density 0.002%

    No Known Activations