© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130346
    Prev
    Next
    INDEX
    Explanations

    tapered

    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_1_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
     Center
    1.02
     οποίο
    0.98
    ann
    0.94
    ن
    0.93
    t
    0.93
     Training
    0.93
    ня
    0.92
     Disclosure
    0.91
    烜
    0.91
    art
    0.90
    POSITIVE LOGITS
    ۔
    1.56
    З
    1.45
    D
    1.18
    は
    1.18
    T
    1.16
    ።
    1.16
    ب
    1.15
    ために
    1.14
    I
    1.14
    고
    1.14
    Activations Density 0.000%

    No Known Activations