© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53085
    Prev
    Next
    INDEX
    Explanations

    batter makes contact

    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_31_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
     Абра
    0.44
     blades
    0.44
     Nil
    0.43
    cimentos
    0.43
     blade
    0.41
     Kamera
    0.40
     Германии
    0.40
    刀
    0.39
     Blade
    0.38
     Enroll
    0.38
    POSITIVE LOGITS
     Decorative
    0.38
     осіб
    0.36
     hof
    0.36
    oupe
    0.35
    upan
    0.35
    hof
    0.34
    ૈય
    0.34
     خۆ
    0.33
     polyclonal
    0.33
    atic
    0.33
    Activations Density 0.027%

    No Known Activations