© 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. 216798
    Prev
    Next
    INDEX
    Explanations

    say \"

    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
     bern
    0.40
    enade
    0.38
    bern
    0.37
    тение
    0.37
    gado
    0.36
     resource
    0.36
    ț
    0.35
    creto
    0.35
    //////////////
    0.35
    gebung
    0.35
    POSITIVE LOGITS
    ವಿ
    0.40
    ‹
    0.40
     جديدة
    0.38
     ultimi
    0.37
     AQ
    0.37
     inciting
    0.37
     nuove
    0.37
    endif
    0.36
    कियां
    0.36
     विप
    0.36
    Activations Density 0.001%

    No Known Activations