© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50152
    Prev
    Next
    INDEX
    Explanations

    print start or path exists

    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_30_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
    وریت
    0.37
    라운
    0.37
    ylamine
    0.36
    }$).
    0.35
    붕
    0.35
     Wink
    0.35
     ہوج
    0.34
     relax
    0.34
    <0x97>
    0.33
     проявля
    0.33
    POSITIVE LOGITS
    opis
    0.34
     fondamental
    0.34
     kar
    0.33
     ley
    0.33
    iving
    0.32
    Living
    0.32
     Orrell
    0.32
    ople
    0.31
     SOCIETY
    0.31
     головы
    0.31
    Activations Density 0.050%

    No Known Activations