© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195105
    Prev
    Next
    INDEX
    Explanations

    sure or afraid

    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_4_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
    يل
    1.10
    ح
    0.89
    سك
    0.88
    كل
    0.88
    ين
    0.87
    ב
    0.85
    الى
    0.85
    يع
    0.84
    كه
    0.84
     člán
    0.84
    POSITIVE LOGITS
    for
    0.86
    ۰۰
    0.84
    ۰
    0.84
    کی
    0.76
    ०
    0.75
    rip
    0.71
    rie
    0.70
     یا
    0.70
    dilation
    0.68
     ऐतिहासिक
    0.68
    Activations Density 0.003%

    No Known Activations