© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62493
    Prev
    Next
    INDEX
    Explanations

    Palestinian Authority

    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_41_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
    落
    0.41
     tense
    0.38
    archar
    0.38
     Serialize
    0.37
    eof
    0.37
     अदर
    0.36
    ేక
    0.36
     serialization
    0.36
    serialize
    0.35
    賬
    0.35
    POSITIVE LOGITS
     PA
    0.78
     Pennsylvania
    0.70
    Pennsylvania
    0.63
    PA
    0.62
     Authority
    0.54
     Palestinian
    0.52
    Authority
    0.52
     Palest
    0.47
     Ramona
    0.47
     اتھار
    0.47
    Activations Density 0.000%

    No Known Activations