© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27931
    Prev
    Next
    INDEX
    Explanations

    Indonesian silakan, Korean manhole, political polarization

    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_10_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
    Laptop
    0.50
    ﻃ
    0.49
    లె
    0.47
    늑
    0.46
    Lily
    0.45
    Port
    0.44
     Sterling
    0.43
    Revolution
    0.43
     Parnell
    0.43
    t
    0.43
    POSITIVE LOGITS
     માટે
    0.53
    творення
    0.50
    substituted
    0.49
    ociety
    0.49
     прису
    0.46
    backgroundSplit
    0.46
     baat
    0.45
    śla
    0.44
    abody
    0.43
    ための
    0.42
    Activations Density 0.000%

    No Known Activations