© 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. 210046
    Prev
    Next
    INDEX
    Explanations

    Post-it Notes

    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
     I
    1.47
    "
    1.23
    SE
    1.17
    ))
    1.14
    \
    1.09
     P
    1.07
     that
    1.02
    PE
    0.99
     T
    0.98
     you
    0.98
    POSITIVE LOGITS
    는
    1.41
    де
    1.36
    niveau
    1.20
    n
    1.18
    de
    1.16
    nymi
    1.16
    maßnahmen
    1.15
    ны
    1.14
    τή
    1.13
    nými
    1.13
    Activations Density 0.000%

    No Known Activations