© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223186
    Prev
    Next
    INDEX
    Explanations

    two part phrases

    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_10_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
     Hanya
    0.52
     J
    0.49
     farklı
    0.48
    Thi
    0.48
     mehrere
    0.47
     GED
    0.47
     H
    0.47
     Audio
    0.47
     Gag
    0.47
     objekt
    0.47
    POSITIVE LOGITS
    ውን
    0.50
    fuse
    0.47
     вы
    0.46
     supremely
    0.45
    pertension
    0.45
     artériel
    0.44
    晖
    0.44
     которому
    0.43
     deliciously
    0.42
    enderita
    0.42
    Activations Density 0.000%

    No Known Activations