© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68341
    Prev
    Next
    INDEX
    Explanations

    tables

    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
     போல
    0.42
     आरएस
    0.38
    ماغ
    0.38
     Folks
    0.38
    শ্য
    0.37
    zees
    0.37
     sensibilité
    0.36
    ť
    0.36
    சூ
    0.36
    ச்ச
    0.36
    POSITIVE LOGITS
    畩
    0.39
    ipotent
    0.38
     $\%
    0.38
    いた
    0.37
     gon
    0.37
    ละคร
    0.37
    ⁶
    0.37
     rower
    0.36
    onter
    0.35
     Goldman
    0.35
    Activations Density 0.003%

    No Known Activations