© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136701
    Prev
    Next
    INDEX
    Explanations

    winner takes it all

    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_12_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
    giraffe
    0.52
     වඩා
    0.49
    idze
    0.48
     d
    0.48
    kwik
    0.48
    เปลี่ยนแปลง
    0.48
    ubar
    0.47
    curvature
    0.47
    THA
    0.47
    ありました
    0.47
    POSITIVE LOGITS
     envo
    0.54
     Josephson
    0.53
    炼
    0.53
     canons
    0.52
     outraged
    0.52
     antiv
    0.50
     decrypted
    0.50
     способ
    0.50
     plutonium
    0.49
     propulsion
    0.48
    Activations Density 0.000%

    No Known Activations