© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156692
    Prev
    Next
    INDEX
    Explanations

    erotic weight gain

    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_2_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
    大
    1.21
    ır
    1.13
    t
    1.06
    ت
    1.06
    ก
    1.05
    aine
    1.04
    ire
    1.02
    ได้
    1.02
    മ
    1.01
    ED
    0.98
    POSITIVE LOGITS
    ۔
    1.55
    s
    1.54
    ри
    1.47
    ли
    1.45
    1.34
    ی
    1.25
    soldiers
    1.22
     a
    1.15
    ні
    1.15
    ি
    1.14
    Activations Density 0.002%

    No Known Activations