© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175849
    Prev
    Next
    INDEX
    Explanations

    lists and papers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    曲
    0.67
     K
    0.67
     ve
    0.61
     곡
    0.57
     曲
    0.54
     curving
    0.52
    Curve
    0.51
    곡
    0.51
     curv
    0.50
     curve
    0.50
    POSITIVE LOGITS
     baixar
    0.41
    Rusty
    0.40
    ڑھ
    0.39
     Rusty
    0.39
     Yong
    0.38
    Syst
    0.38
     بچ
    0.37
     leverage
    0.37
     syst
    0.37
    ncia
    0.37
    Activations Density 0.005%

    No Known Activations