© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127107
    Prev
    Next
    INDEX
    Explanations

    titillation, latex, TeX

    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_3_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
    Petrol
    0.77
    SGD
    0.75
    UD
    0.70
    IR
    0.70
    SY
    0.70
    મ
    0.68
    UP
    0.67
     Ini
    0.67
    Ini
    0.67
    IM
    0.66
    POSITIVE LOGITS
     mà
    0.60
     মাধ্যম
    0.58
     drastic
    0.57
     đáng
    0.57
     painfully
    0.56
     prejudiced
    0.56
    ى
    0.56
    nej
    0.55
    ной
    0.55
     shocking
    0.55
    Activations Density 0.000%

    No Known Activations