© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43193
    Prev
    Next
    INDEX
    Explanations

    numbers and technical specifications

    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_3_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
    y
    0.75
    nie
    0.70
    LEASE
    0.70
    yiz
    0.70
    ni
    0.69
    d
    0.69
    n
    0.68
    lük
    0.66
    o
    0.66
    ний
    0.65
    POSITIVE LOGITS
    י
    0.91
    ी
    0.82
    ร
    0.73
    И
    0.72
    ي
    0.70
     be
    0.70
    ி
    0.68
     reçoit
    0.67
    って
    0.66
    Y
    0.66
    Activations Density 0.024%

    No Known Activations