© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120580
    Prev
    Next
    INDEX
    Explanations

    rewriting concise

    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_27_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
     বিচারের
    0.38
     coerc
    0.36
     forgiveness
    0.34
     utwor
    0.34
     rash
    0.33
    薪
    0.33
     bancos
    0.32
    xon
    0.32
     unst
    0.31
     Controlled
    0.31
    POSITIVE LOGITS
     おはよう
    0.38
    жность
    0.38
     আমন্ত্রণ
    0.38
    ೯
    0.35
     slows
    0.34
    bloom
    0.34
    жная
    0.34
    otional
    0.33
    angle
    0.33
    ductor
    0.33
    Activations Density 0.046%

    No Known Activations