© 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. 122904
    Prev
    Next
    INDEX
    Explanations

    medicated, ball, India, Nutrition

    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
     dificult
    0.74
     passou
    0.72
     continuare
    0.71
    ﺎ
    0.71
     retirada
    0.71
    व
    0.71
     conhe
    0.70
    ため
    0.69
    ﻊ
    0.69
     puestos
    0.68
    POSITIVE LOGITS
    ال
    0.85
    ان
    0.80
    EL
    0.80
    an
    0.78
    c
    0.77
    it
    0.73
    AR
    0.72
    städ
    0.71
    s
    0.71
    AT
    0.71
    Activations Density 0.001%

    No Known Activations