© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230348
    Prev
    Next
    INDEX
    Explanations

    Vercel, Netlify, Next.js, AI

    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_6_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
     bosques
    1.16
     impuestos
    1.15
    نق
    1.12
    د
    1.11
     государ
    1.10
    ص
    1.10
     волосы
    1.09
    eské
    1.08
     proposés
    1.08
     juguetes
    1.06
    POSITIVE LOGITS
    ↵
    1.10
    ed
    0.96
    Α
    0.93
    er
    0.93
    the
    0.86
    ่
    0.84
    …
    0.84
    -
    0.83
    ৯
    0.83
    ACH
    0.77
    Activations Density 0.000%

    No Known Activations