© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174324
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    夋
    0.45
    शंस
    0.44
     Еўропы
    0.42
     Inoltre
    0.41
    сад
    0.41
    额外
    0.41
    เที่
    0.40
    atip
    0.40
     днів
    0.40
    امن
    0.40
    POSITIVE LOGITS
    _\
    0.44
    \
    0.42
     liver
    0.42
    ritte
    0.42
     Pourquoi
    0.42
    是因为
    0.41
     ins
    0.40
     precipitate
    0.40
    oyl
    0.40
     ili
    0.39
    Activations Density 0.000%

    No Known Activations