© 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. 202315
    Prev
    Next
    INDEX
    Explanations

    without losing or modifying

    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
    rom
    0.55
    ral
    0.55
    ois
    0.55
    、
    0.55
    have
    0.54
    னின்
    0.52
    arkan
    0.51
    ного
    0.51
    。
    0.51
    usr
    0.50
    POSITIVE LOGITS
     contou
    0.73
     to
    0.64
    사
    0.63
    자
    0.63
     abril
    0.61
    대
    0.61
     апре
    0.60
    ಬ
    0.60
     اكثر
    0.60
     ouvrir
    0.60
    Activations Density 0.013%

    No Known Activations