© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 37147
    Prev
    Next
    INDEX
    Explanations

    arbitrary data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    𝐽
    0.36
    כ
    0.36
    zków
    0.36
     Promote
    0.35
    iorno
    0.34
    伎
    0.33
    ployee
    0.33
    volve
    0.33
    ięcy
    0.33
    ognito
    0.32
    POSITIVE LOGITS
    </a>
    0.37
     atan
    0.36
    TNumber
    0.35
     Ron
    0.34
     Nin
    0.34
     Hank
    0.34
     rin
    0.34
     LUT
    0.34
    Hank
    0.34
    sas
    0.33
    Activations Density 0.214%

    No Known Activations