© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174541
    Prev
    Next
    INDEX
    Explanations

    Statista

    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_20_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
     লীগ
    0.46
    ابقات
    0.46
     രാഷ്ട്രീയ
    0.44
    ාවක්
    0.43
    вете
    0.42
    یات
    0.42
     محکمہ
    0.42
    ͤ
    0.42
     pname
    0.42
    isotropic
    0.42
    POSITIVE LOGITS
    過
    0.49
     Pharmac
    0.49
    两
    0.48
    过
    0.47
    的一
    0.45
    endon
    0.44
     Savage
    0.44
     Edson
    0.44
     Cardinal
    0.44
    Pharmac
    0.43
    Activations Density 0.000%

    No Known Activations