© 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. 218516
    Prev
    Next
    INDEX
    Explanations

    command smart devices

    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
    Be
    0.38
    劈
    0.37
    Net
    0.36
     sandalwood
    0.36
     W
    0.35
    REME
    0.35
     remettre
    0.35
     가게
    0.35
    TopOf
    0.35
     toilet
    0.35
    POSITIVE LOGITS
     Bedrooms
    0.40
     条件
    0.40
     dormitorio
    0.39
    omètre
    0.39
    တတ်
    0.38
     Ciencias
    0.38
    ⑥
    0.37
    स्वा
    0.37
     chicas
    0.36
     क्षमताओं
    0.36
    Activations Density 0.004%

    No Known Activations