© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31866
    Prev
    Next
    INDEX
    Explanations

    code components

    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_50_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
     এইচ
    0.32
     VM
    0.29
    ?')
    0.29
     μα
    0.28
     DSM
    0.27
     डीएस
    0.27
     storica
    0.27
     η
    0.27
     zona
    0.27
     своего
    0.26
    POSITIVE LOGITS
    ンダント
    0.26
    ্যাল
    0.23
    новение
    0.23
    твра
    0.23
    شنبه
    0.23
    遍
    0.23
    scdn
    0.22
    тента
    0.22
    iap
    0.22
    pekte
    0.22
    Activations Density 0.005%

    No Known Activations