© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195849
    Prev
    Next
    INDEX
    Explanations

    anthropomorphic animals

    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_46_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
    สัง
    0.37
    obank
    0.37
    ク
    0.36
    shen
    0.35
    चिंत
    0.35
     St
    0.34
    贫
    0.34
    pots
    0.34
    aménagement
    0.33
    useum
    0.33
    POSITIVE LOGITS
    volta
    0.46
     leop
    0.40
     bolted
    0.39
    岨
    0.37
     bio
    0.37
    毗
    0.37
    IDF
    0.37
     общественных
    0.37
    虎
    0.37
    স্বরূপ
    0.36
    Activations Density 0.007%

    No Known Activations