© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35147
    Prev
    Next
    INDEX
    Explanations

    hazard statements

    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
    ights
    0.57
    ktionen
    0.54
    I
    0.54
    arly
    0.54
    iger
    0.53
    .
    0.53
    ઠળ
    0.52
    aily
    0.52
    你去
    0.52
    ucid
    0.51
    POSITIVE LOGITS
    ные
    0.71
    ‌های
    0.70
    ુ
    0.68
    ні
    0.68
     immobilier
    0.66
    erreur
    0.64
     scolaire
    0.64
    ר
    0.64
    وں
    0.63
    ле
    0.63
    Activations Density 0.001%

    No Known Activations