© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45947
    Prev
    Next
    INDEX
    Explanations

    fishy taste

    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_13_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
    centres
    0.53
     bonnes
    0.52
    撣
    0.50
    𝗗
    0.49
    handedly
    0.48
    ྛ
    0.47
    Dieter
    0.46
    Hive
    0.46
    WOOD
    0.46
    graduation
    0.46
    POSITIVE LOGITS
     at
    0.62
     Tehran
    0.59
    ร
    0.56
     ร
    0.54
     cuire
    0.54
    ată
    0.53
    arken
    0.53
     Rojo
    0.52
     mondial
    0.52
    तों
    0.52
    Activations Density 0.004%

    No Known Activations