© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5879
    Prev
    Next
    INDEX
    Explanations

    central religious themes

    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_39_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
    評価
    0.39
    TRUE
    0.38
    막
    0.36
    真正
    0.36
    传说
    0.36
    ʏ
    0.35
    true
    0.34
    真正的
    0.34
    凑
    0.34
     numerador
    0.34
    POSITIVE LOGITS
     divine
    0.48
     central
    0.47
     центра
    0.47
    Divine
    0.47
     Divine
    0.46
     centrale
    0.44
     theological
    0.43
     religious
    0.43
    פתח
    0.42
     divino
    0.41
    Activations Density 0.115%

    No Known Activations