© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202778
    Prev
    Next
    INDEX
    Explanations

    4

    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_46_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
     தாக்கு
    0.35
     रिय
    0.35
     福
    0.34
     ورلڈ
    0.34
     இறை
    0.33
     Desenvolvimento
    0.33
    وڑا
    0.33
     fuit
    0.33
     puente
    0.33
    ందో
    0.32
    POSITIVE LOGITS
    5
    0.49
    
    0.44
    
    0.44
     خمسه
    0.42
     пять
    0.41
    ૫
    0.40
    ٥
    0.40
     cinco
    0.39
     پنج
    0.39
     Five
    0.38
    Activations Density 0.000%

    No Known Activations