© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41625
    Prev
    Next
    INDEX
    Explanations

    parenthetical remarks

    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_22_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
    高等
    0.20
     मनोर
    0.20
     خواهد
    0.20
    йда
    0.19
     elegante
    0.19
    台
    0.19
     montre
    0.19
     முதல
    0.19
     دانشگاه
    0.18
    月
    0.18
    POSITIVE LOGITS
     youre
    0.20
     Freeway
    0.20
     occur
    0.19
    Smartphone
    0.19
     versus
    0.18
    RewardedVideo
    0.18
    versus
    0.18
    Ss
    0.18
    Bluetooth
    0.18
    werp
    0.18
    Activations Density 0.000%

    No Known Activations