© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57470
    Prev
    Next
    INDEX
    Explanations

    Habib and Khalil names

    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_11_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
    қта
    0.60
    ぐ
    0.59
    кистон
    0.58
    кован
    0.56
    c
    0.55
    game
    0.55
    encoders
    0.54
    ćen
    0.54
    dont
    0.54
    дування
    0.54
    POSITIVE LOGITS
     soloist
    0.60
     ().
    0.58
    나
    0.57
     Athena
    0.56
     lymphatiques
    0.55
    னி
    0.55
    <0x98>
    0.54
     ])
    0.54
     XII
    0.54
     acetylcholine
    0.54
    Activations Density 0.000%

    No Known Activations