© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209415
    Prev
    Next
    INDEX
    Explanations

    equal or now

    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_10_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
    ad
    1.23
    st
    0.96
    r
    0.90
    s
    0.90
    z
    0.89
    pe
    0.88
    y
    0.88
    f
    0.87
    n
    0.87
    t
    0.85
    POSITIVE LOGITS
     coffers
    0.95
     ו
    0.88
    もら
    0.87
     மற்றும்
    0.84
     divides
    0.83
     comptes
    0.82
     wynik
    0.82
     wyniki
    0.81
    ри
    0.80
     και
    0.80
    Activations Density 0.000%

    No Known Activations