© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158187
    Prev
    Next
    INDEX
    Explanations

    asked questions

    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_2_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
    )
    1.13
    ानी
    0.99
    ۰
    0.96
    K
    0.94
    z
    0.92
     dirig
    0.89
    di
    0.88
    OUT
    0.88
    din
    0.85
     Pestic
    0.84
    POSITIVE LOGITS
    ة
    1.56
    ン
    1.47
    خ
    1.43
    ב
    1.42
    н
    1.35
    ה
    1.34
    ب
    1.31
    й
    1.31
    ۔
    1.27
    は
    1.27
    Activations Density 0.001%

    No Known Activations