© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207082
    Prev
    Next
    INDEX
    Explanations

    python import statements

    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_20_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
     ありがとう
    0.37
     Hike
    0.37
    œ
    0.37
    same
    0.36
    CQ
    0.36
     manicure
    0.36
    pandemic
    0.36
     Sop
    0.36
    posting
    0.36
    дав
    0.35
    POSITIVE LOGITS
    미
    0.44
    İN
    0.42
    ється
    0.41
    இ
    0.40
     détail
    0.38
    İM
    0.38
     ř
    0.38
    ರಲ್ಲಿ
    0.37
    潇
    0.37
     미
    0.36
    Activations Density 0.002%

    No Known Activations