© 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. 89771
    Prev
    Next
    INDEX
    Explanations

    today

    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
     *}
    0.59
    ()}
    0.55
     게
    0.55
     회
    0.54
     ihe
    0.54
    攽
    0.54
     aren
    0.53
     ними
    0.53
     پڑے
    0.53
     Peoples
    0.52
    POSITIVE LOGITS
    t
    0.88
    to
    0.82
    ين
    0.82
     residentes
    0.80
    то
    0.79
     visitantes
    0.77
    g
    0.73
    m
    0.71
    т
    0.71
    со
    0.71
    Activations Density 0.001%

    No Known Activations