© 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. 50102
    Prev
    Next
    INDEX
    Explanations

    your [role/description]

    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
    Cryptography
    0.40
    пе
    0.38
    ->__
    0.38
     करावी
    0.37
     ratios
    0.35
    積み
    0.35
     trainers
    0.34
    勹
    0.34
     ತೆಗೆದುಕೊಳ್ಳ
    0.33
    買って
    0.32
    POSITIVE LOGITS
    empor
    0.41
    urbance
    0.40
     confid
    0.38
     Airborne
    0.38
     meinen
    0.38
     inesper
    0.38
     ہمارا
    0.38
     access
    0.37
     nosso
    0.37
     aigu
    0.37
    Activations Density 0.007%

    No Known Activations