© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2778
    Prev
    Next
    INDEX
    Explanations

    numbers within parentheses

    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_40_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
    cita
    0.25
    ++)//
    0.24
    Invoice
    0.24
     putting
    0.23
    ্ভ
    0.23
    )(-
    0.23
    outil
    0.22
    ம்பரிய
    0.22
     psicológica
    0.22
     mín
    0.22
    POSITIVE LOGITS
     చూపు
    0.26
     AFI
    0.26
     =======
    0.25
     Early
    0.25
     finden
    0.24
    再
    0.24
     affects
    0.24
     organizes
    0.24
     finds
    0.24
     Broadband
    0.23
    Activations Density 0.003%

    No Known Activations