© 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. 197518
    Prev
    Next
    INDEX
    Explanations

    animal sounds

    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
    运维
    0.43
     velocidades
    0.43
     OTA
    0.42
     šť
    0.39
    🦓
    0.38
    otrans
    0.38
    吊
    0.37
     دا
    0.37
    owitz
    0.36
     Ata
    0.36
    POSITIVE LOGITS
    AMM
    0.45
     آم
    0.40
    ama
    0.40
    agi
    0.39
    AM
    0.39
    امة
    0.38
     Scalar
    0.38
    ार्क
    0.37
     అమ
    0.37
    ম
    0.37
    Activations Density 0.009%

    No Known Activations