© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75505
    Prev
    Next
    INDEX
    Explanations

    closing delimiters followed by code structures

    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_31_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
     primero
    0.40
     контек
    0.37
    ontology
    0.36
     polym
    0.36
    usingCamera
    0.36
    }`)
    0.36
     pellets
    0.36
     razum
    0.36
     formContext
    0.36
     sensitive
    0.35
    POSITIVE LOGITS
    igde
    0.37
     угла
    0.36
    加快
    0.35
    座
    0.35
     Conseils
    0.35
     Kampung
    0.34
     कैंप
    0.34
     ক্যাম্প
    0.34
     संतोष
    0.34
    regation
    0.33
    Activations Density 0.002%

    No Known Activations