© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236381
    Prev
    Next
    INDEX
    Explanations

    data structure definitions

    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_25_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
    軒
    0.39
    まま
    0.37
     Pobl
    0.37
    ﯼ
    0.37
     subscribing
    0.35
     incrementally
    0.35
    နေရာ
    0.35
    辂
    0.35
    镍
    0.34
     detrimental
    0.34
    POSITIVE LOGITS
     디자인
    0.41
     कैपिट
    0.39
    പ്പെടുത്ത
    0.37
     设计
    0.37
     لان
    0.37
    iens
    0.36
     dược
    0.36
    펩
    0.35
    راضي
    0.34
     gern
    0.34
    Activations Density 0.003%

    No Known Activations