© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23888
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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_56_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
     post
    0.33
     Post
    0.31
     (:
    0.31
     पोस्ट
    0.30
     ?)
    0.30
    ポスト
    0.30
     (;
    0.30
    post
    0.29
    Post
    0.29
    〕
    0.28
    POSITIVE LOGITS
     maupun
    0.39
    𝓹
    0.36
     ataupun
    0.35
    haltens
    0.34
    PS
    0.33
    otification
    0.32
     PS
    0.32
    ्तीय
    0.32
     trá
    0.32
    ./
    0.32
    Activations Density 0.041%

    No Known Activations