© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219081
    Prev
    Next
    INDEX
    Explanations

    numbers and common prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    rift
    0.37
    uland
    0.35
    sty
    0.35
    近代
    0.35
     paints
    0.35
    UMIRE
    0.34
    蝶
    0.34
    itioner
    0.34
    ्डा
    0.34
    imped
    0.34
    POSITIVE LOGITS
     $|\
    0.43
     چو
    0.38
    ؟
    0.37
     Follow
    0.36
     McCall
    0.35
     எல்லா
    0.34
     लॉकडाउन
    0.34
     $\|\
    0.34
     Zombies
    0.34
    ယူ
    0.33
    Activations Density 0.001%

    No Known Activations