© 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. 41557
    Prev
    Next
    INDEX
    Explanations

    "Use X words"

    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
    장은
    0.16
    
    0.16
     proprietor
    0.15
     erection
    0.15
     கரைச
    0.15
     estabelecer
    0.15
    샨
    0.15
     о
    0.14
    epage
    0.14
     felt
    0.14
    POSITIVE LOGITS
    Possibly
    0.15
    consuming
    0.15
    Plus
    0.15
    thys
    0.15
    INTE
    0.15
    TIA
    0.14
    excluding
    0.14
    Cómo
    0.14
    Especially
    0.14
    জ্ঞ
    0.14
    Activations Density 0.003%

    No Known Activations