© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46741
    Prev
    Next
    INDEX
    Explanations

    consume token or input

    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_13_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
     Shortly
    0.34
    ver
    0.32
    ring
    0.32
     ONE
    0.32
     Brazil
    0.32
     =
    0.31
     Regional
    0.31
    ni
    0.31
     Professional
    0.31
     In
    0.31
    POSITIVE LOGITS
    enery
    0.40
    ת
    0.39
    ேட்
    0.38
    wikk
    0.34
    as
    0.32
    டன்
    0.32
    䀖
    0.32
    wikidata
    0.31
     moneys
    0.31
    etches
    0.31
    Activations Density 0.004%

    No Known Activations