© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216008
    Prev
    Next
    INDEX
    Explanations

    read code

    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_50_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
     Jessie
    0.41
     Angelica
    0.41
     cayenne
    0.41
     pepe
    0.40
    ಿಕೆಯ
    0.39
     Jesse
    0.38
     Hester
    0.38
    <0x85>
    0.38
     Dorothy
    0.38
     Doom
    0.38
    POSITIVE LOGITS
    nats
    0.43
    合理的
    0.39
    apd
    0.39
     reasonable
    0.38
    stre
    0.36
     optio
    0.36
    facing
    0.36
    нат
    0.36
     limited
    0.35
     cui
    0.35
    Activations Density 0.000%

    No Known Activations