© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62166
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_59_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
     EdgeInsets
    0.31
    ুব্ধ
    0.30
    膊
    0.29
    衅
    0.29
    astically
    0.29
     getData
    0.29
     உண்டா
    0.28
    텁
    0.28
     getUser
    0.28
    が必要
    0.28
    POSITIVE LOGITS
    ٬
    0.96
     ፣
    0.95
    ،
    0.92
    ‌,
    0.88
    ､
    0.88
    ፣
    0.86
     ،
    0.84
    ‚
    0.81
    ,\
    0.80
    ,​
    0.80
    Activations Density 0.040%

    No Known Activations