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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63498
    Prev
    Next
    INDEX
    Explanations

    rational basis test

    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
    මින්
    0.41
    TestingModule
    0.39
     ২১
    0.38
    📏
    0.38
    窮
    0.38
     suspect
    0.38
    🗣
    0.38
    늉
    0.37
    უკ
    0.37
     diligence
    0.36
    POSITIVE LOGITS
     Rational
    0.64
    Rational
    0.64
    rational
    0.62
     rational
    0.60
     rationally
    0.58
     rationality
    0.53
     racional
    0.46
     рациона
    0.43
     racionais
    0.40
     rationalize
    0.39
    Activations Density 0.001%

    No Known Activations