© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237431
    Prev
    Next
    INDEX
    Explanations

    conditional logic statements

    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_25_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
     nebo
    0.47
     atau
    0.46
     vagy
    0.43
     或
    0.42
    或
    0.42
     αλλά
    0.41
     και
    0.41
     và
    0.41
     અથવા
    0.40
     oder
    0.40
    POSITIVE LOGITS
     controversy
    0.47
     ACCEPT
    0.39
    വദ
    0.37
     Controversy
    0.37
    boilerplate
    0.36
     वडिला
    0.36
     reports
    0.36
     বক্তব
    0.36
     hotly
    0.36
    璞
    0.35
    Activations Density 0.002%

    No Known Activations