© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130565
    Prev
    Next
    INDEX
    Explanations

    delicate, extremely, excessive

    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_6_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
     to
    1.13
    ש
    1.08
    ف
    1.03
    า
    0.98
    ם
    0.93
    וד
    0.90
    س
    0.89
    다
    0.88
    ך
    0.86
     was
    0.86
    POSITIVE LOGITS
     انتہائی
    0.88
     extremadamente
    0.87
     अत्यधिक
    0.86
     ενός
    0.86
    Α
    0.85
    gruppe
    0.83
    g
    0.83
    daki
    0.82
     Maugin
    0.82
    ges
    0.82
    Activations Density 0.000%

    No Known Activations