© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177509
    Prev
    Next
    INDEX
    Explanations

    rational vs irrational numbers, variables, bounds

    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_24_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
     modification
    0.47
     mutation
    0.44
    욜
    0.42
     dispensation
    0.41
     canonical
    0.39
     fanáticos
    0.39
     contextual
    0.37
     malas
    0.37
     imediatamente
    0.37
     길
    0.37
    POSITIVE LOGITS
    брать
    0.44
    热爱
    0.41
    مي
    0.40
    agoza
    0.39
     Harvest
    0.39
    事业
    0.38
    حصل
    0.38
    縮
    0.38
     RMA
    0.38
     Herb
    0.37
    Activations Density 0.000%

    No Known Activations