© 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. 36571
    Prev
    Next
    INDEX
    Explanations

    Form

    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
     Freedman
    0.41
    Genome
    0.38
    haus
    0.37
    稣
    0.37
    တွ
    0.37
    kee
    0.37
     uni
    0.37
    тельным
    0.37
    堂
    0.36
    断面
    0.36
    POSITIVE LOGITS
    coid
    0.47
    apun
    0.38
     grundsätzlich
    0.38
     देओल
    0.38
     stella
    0.38
    ConstPtr
    0.38
     Kira
    0.38
    ColorEffects
    0.38
     звезды
    0.37
     appoints
    0.36
    Activations Density 0.001%

    No Known Activations