© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180992
    Prev
    Next
    INDEX
    Explanations

    comment markers

    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_29_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
     KW
    0.40
     cud
    0.38
    入り
    0.38
     বাধ
    0.37
    ಿಸುತ್ತ
    0.36
     Houghton
    0.36
     الواحده
    0.35
    ፤
    0.35
    owej
    0.35
     Cud
    0.35
    POSITIVE LOGITS
     особен
    0.39
    Zi
    0.39
    䣵
    0.38
     अपेक्षाकृत
    0.38
     följande
    0.37
    slightly
    0.37
     mắt
    0.37
     слегка
    0.36
    alc
    0.36
    зи
    0.36
    Activations Density 0.001%

    No Known Activations