© 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. 45955
    Prev
    Next
    INDEX
    Explanations

    form generator, document management, duplicate ids

    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
     quieter
    0.38
    મેન્ટ
    0.38
     repeatable
    0.35
    辑
    0.35
    ogenicity
    0.34
    িপি
    0.34
     grammaticality
    0.34
     repeatability
    0.33
    Eppo
    0.33
    jectory
    0.33
    POSITIVE LOGITS
     |
    0.35
     साम्राज्य
    0.35
     दर्जन
    0.34
     organismo
    0.33
     thrill
    0.32
     aucun
    0.31
     financiers
    0.31
     cov
    0.31
     empires
    0.31
     أش
    0.30
    Activations Density 0.000%

    No Known Activations