© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66841
    Prev
    Next
    INDEX
    Explanations

    name parts

    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_51_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
     Platform
    0.38
     Sitz
    0.38
    /'+
    0.38
     Stol
    0.37
    ky
    0.37
    Hudson
    0.37
    clearRect
    0.37
     platform
    0.36
     অর্
    0.36
    Al
    0.36
    POSITIVE LOGITS
    abri
    0.42
    कर्षण
    0.39
    OVERRIDES
    0.38
    arasi
    0.38
    èles
    0.38
    மணிய
    0.38
     Rast
    0.38
    룀
    0.38
     jdk
    0.37
    骼
    0.37
    Activations Density 0.000%

    No Known Activations