© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11218
    Prev
    Next
    INDEX
    Explanations

    blade, teeth, comb

    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_13_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
    滹
    0.51
    āna
    0.49
     hemorrhage
    0.49
    𝑡
    0.49
     মৃত্যু
    0.48
     Sulfur
    0.48
     темно
    0.47
    him
    0.46
     интер
    0.46
    αρ
    0.46
    POSITIVE LOGITS
     pokud
    0.50
     hvis
    0.49
    焼け
    0.49
    யில
    0.49
     אם
    0.49
     اگر
    0.47
    مل
    0.47
    読
    0.44
    ﺵ
    0.44
     jika
    0.44
    Activations Density 0.017%

    No Known Activations