© 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. 218637
    Prev
    Next
    INDEX
    Explanations

    Board

    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
     板
    0.43
    awesi
    0.42
    ياء
    0.40
     الرجل
    0.39
     Plano
    0.39
    倆
    0.38
    🦎
    0.38
    ার্ড
    0.37
    板
    0.37
     Board
    0.37
    POSITIVE LOGITS
     blocking
    0.39
    치의
    0.39
     identity
    0.38
    سور
    0.36
     CBI
    0.36
    त्रा
    0.36
     SCO
    0.35
    gpg
    0.35
     ladle
    0.35
     อำ
    0.35
    Activations Density 0.000%

    No Known Activations