© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78441
    Prev
    Next
    INDEX
    Explanations

    fascinating and ... phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
    لاس
    0.43
     would
    0.42
    领
    0.41
    हाला
    0.40
     چلا
    0.39
     departe
    0.39
     skulle
    0.39
    さすが
    0.39
     though
    0.38
     യ
    0.38
    POSITIVE LOGITS
    Hist
    0.39
     सांसदों
    0.38
    Height
    0.37
    Donald
    0.35
    Urls
    0.34
     отношениях
    0.34
    Watts
    0.34
    Horse
    0.33
     уены
    0.33
    REQUI
    0.33
    Activations Density 0.044%

    No Known Activations