© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15624
    Prev
    Next
    INDEX
    Explanations

    online activity

    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_15_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
     கீ
    0.55
    ises
    0.52
    बित
    0.52
    ﻊ
    0.50
     ríos
    0.50
    ies
    0.49
    urg
    0.48
    珂
    0.47
     Dör
    0.47
    hesion
    0.47
    POSITIVE LOGITS
    ש
    0.52
     Lamin
    0.52
     userdata
    0.51
    اح
    0.50
     XP
    0.48
     xp
    0.48
     funktionieren
    0.47
    aii
    0.47
     detta
    0.47
    ج
    0.47
    Activations Density 0.015%

    No Known Activations