© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225847
    Prev
    Next
    INDEX
    Explanations

    half-

    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_10_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
     Während
    0.41
    ר
    0.41
     }^{
    0.39
     Etat
    0.39
    יי
    0.38
     metallurgical
    0.38
     Fuels
    0.37
    र
    0.37
     flotte
    0.37
    ু
    0.37
    POSITIVE LOGITS
     not
    0.39
    es
    0.36
    с
    0.36
     В
    0.36
    ON
    0.35
     야
    0.35
    exp
    0.34
    os
    0.33
    ex
    0.33
    navigation
    0.33
    Activations Density 0.002%

    No Known Activations