© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149837
    Prev
    Next
    INDEX
    Explanations

    reversing text

    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_59_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
    jem
    0.45
    gens
    0.44
    cmp
    0.43
    ggbb
    0.41
    gom
    0.41
    gem
    0.41
    鸹
    0.41
    emarks
    0.40
    gbm
    0.40
     Trident
    0.40
    POSITIVE LOGITS
     S
    0.51
    S
    0.47
     C
    0.46
     يَ
    0.46
     הס
    0.43
     С
    0.41
     a
    0.39
     allere
    0.39
    C
    0.38
    0.38
    Activations Density 0.003%

    No Known Activations