© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175392
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
     diciamo
    0.59
    忄
    0.56
    ሎ
    0.54
     uomini
    0.53
    Всім
    0.52
    ıları
    0.51
     diariamente
    0.49
    दिन
    0.49
    रो
    0.49
    |$.
    0.48
    POSITIVE LOGITS
    U
    0.62
     przyp
    0.44
     was
    0.43
    LE
    0.40
    User
    0.40
    s
    0.40
    0
    0.40
     Tw
    0.40
     местных
    0.39
     الع
    0.38
    Activations Density 0.000%

    No Known Activations