© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213611
    Prev
    Next
    INDEX
    Explanations

    small

    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_47_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
     Breg
    0.43
     küçük
    0.42
     маленький
    0.41
     small
    0.40
     tiny
    0.39
     малень
    0.39
    弹性
    0.39
    昊
    0.39
    small
    0.38
     ZA
    0.38
    POSITIVE LOGITS
     फंस
    0.41
    პირ
    0.41
    ('./
    0.40
    estock
    0.37
    Nickel
    0.37
    絹
    0.36
     understood
    0.36
     abiert
    0.35
    Ро
    0.35
    ிற்கு
    0.35
    Activations Density 0.001%

    No Known Activations