© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177103
    Prev
    Next
    INDEX
    Explanations

    music terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     хи
    0.61
    ヒ
    0.50
     हि
    0.48
     Хи
    0.46
     ഹി
    0.44
     히
    0.44
    ҳи
    0.44
    히
    0.43
     Jakob
    0.43
    希
    0.42
    POSITIVE LOGITS
     aort
    0.45
     amel
    0.40
    beat
    0.40
     sopr
    0.40
     CaO
    0.40
     Avenue
    0.39
    Ava
    0.39
    wholesale
    0.39
    THz
    0.39
    cao
    0.39
    Activations Density 0.000%

    No Known Activations