© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35831
    Prev
    Next
    INDEX
    Explanations

    all / everything

    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_11_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
    1
    0.73
     variar
    0.63
     दंप
    0.59
    when
    0.59
    ाइव
    0.56
    Variance
    0.56
     altres
    0.55
    werke
    0.55
     vair
    0.55
    variation
    0.54
    POSITIVE LOGITS
    덟
    0.53
    л
    0.52
    สำหรับ
    0.50
     बर्बाद
    0.50
    ना
    0.50
    사는
    0.49
     futuristic
    0.49
    🙏
    0.49
    <0xA1>
    0.49
     przysz
    0.48
    Activations Density 0.002%

    No Known Activations