© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142606
    Prev
    Next
    INDEX
    Explanations

    database server name

    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_0_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
    ะ
    1.72
    на
    1.64
    ся
    1.64
    ี
    1.64
    ו
    1.60
    ก
    1.57
    ิ
    1.53
    ari
    1.50
    ہ
    1.49
    ס
    1.43
    POSITIVE LOGITS
    ።
    1.28
     (
    1.18
     reorgan
    1.14
    เป็น
    1.13
     caries
    1.12
    欬
    1.09
     fréqu
    1.08
    이다
    1.07
    getVisibility
    1.06
    的产品
    1.05
    Activations Density 0.000%

    No Known Activations