© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79697
    Prev
    Next
    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    стве
    0.38
    ﻁ
    0.38
    ☇
    0.38
    WR
    0.37
    පු
    0.37
     Cym
    0.37
     Grundstück
    0.37
     नर्म
    0.36
    伸縮
    0.36
    牞
    0.35
    POSITIVE LOGITS
     حا
    0.48
    silent
    0.43
     silently
    0.43
     누
    0.42
     silent
    0.40
    စီး
    0.40
     Aix
    0.39
    Checker
    0.38
    marketing
    0.38
     onChanged
    0.38
    Activations Density 0.011%

    No Known Activations