© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199042
    Prev
    Next
    INDEX
    Explanations

    job fields and career paths

    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_27_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
     spesies
    0.40
    त
    0.38
     답변
    0.38
    kort
    0.37
     hir
    0.36
    唁
    0.35
    uação
    0.35
    Species
    0.35
    {(-
    0.35
     பிரதேச
    0.34
    POSITIVE LOGITS
     Miranda
    0.36
    かと思います
    0.36
     commended
    0.36
     внед
    0.36
     Volunte
    0.36
    丽
    0.35
     Salut
    0.35
    рока
    0.34
     Activ
    0.34
    ropic
    0.34
    Activations Density 0.003%

    No Known Activations