© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46838
    Prev
    Next
    INDEX
    Explanations

    truth, honesty, integrity, liars

    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_13_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
     ডাউনলোড
    0.50
    下载
    0.45
    堬
    0.44
     डाउनलोड
    0.44
    ርግ
    0.43
    比亚
    0.43
     যেকোন
    0.42
    ダウンロード
    0.42
    乌
    0.42
    ウ
    0.42
    POSITIVE LOGITS
     scram
    0.46
     Spins
    0.46
    ute
    0.46
     Tama
    0.45
    谎
    0.45
     Bates
    0.45
     UTI
    0.45
    诚信
    0.44
    üh
    0.44
     när
    0.44
    Activations Density 0.107%

    No Known Activations