© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53675
    Prev
    Next
    INDEX
    Explanations

    factor in determining

    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_30_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
    μένα
    0.38
    oken
    0.38
     لج
    0.38
     elaborate
    0.37
    avier
    0.37
     seven
    0.37
    ·
    0.37
    dan
    0.37
     onion
    0.37
    も含
    0.37
    POSITIVE LOGITS
     किन्तु
    0.39
     kecepatan
    0.38
    Cot
    0.38
    uillez
    0.38
     случаев
    0.37
     शा
    0.37
     lekin
    0.36
    ufen
    0.36
    istir
    0.35
    鐮
    0.35
    Activations Density 0.014%

    No Known Activations