© 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. 39517
    Prev
    Next
    INDEX
    Explanations

    HTL, HITL, HTM, HTML

    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
    də
    0.81
    (
    0.79
    dü
    0.73
     renovación
    0.71
    건
    0.69
    anlagen
    0.68
    dependent
    0.67
    خی
    0.67
     făcut
    0.67
    ド
    0.67
    POSITIVE LOGITS
    ية
    0.91
    ى
    0.71
    ite
    0.69
    то
    0.69
    ings
    0.63
    𝐫
    0.62
    iculaire
    0.61
     eens
    0.59
    ρα
    0.57
    iale
    0.57
    Activations Density 0.001%

    No Known Activations