© 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. 163950
    Prev
    Next
    INDEX
    Explanations

    view from the outside

    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
     chef
    0.30
    하면서
    0.29
     zajed
    0.29
     dobbiamo
    0.28
    ளர்
    0.28
     menit
    0.28
     recomendar
    0.28
    ^{(
    0.27
    locationY
    0.27
    を手
    0.27
    POSITIVE LOGITS
    Drawing
    0.31
     طرح
    0.30
     রেশন
    0.30
    йон
    0.30
     Anderson
    0.30
     Browse
    0.30
    duck
    0.29
    زمانہ
    0.29
     Cesar
    0.29
     सख्ती
    0.29
    Activations Density 0.002%

    No Known Activations