© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     ऑक्ट
    0.38
     يوجد
    0.34
     adalah
    0.34
     وقع
    0.34
    Есть
    0.34
     יש
    0.34
     是
    0.33
     είναι
    0.33
     Signaling
    0.32
    
    0.32
    POSITIVE LOGITS
    ᓚ
    0.43
    ALL
    0.42
    All
    0.40
    Flare
    0.39
    विला
    0.38
    Appropri
    0.37
     fooling
    0.37
    APPRO
    0.36
    合适的
    0.36
    thione
    0.35
    Activations Density 0.000%

    No Known Activations