© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5529
    Prev
    Next
    INDEX
    Explanations

    flutter code

    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_40_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
    Consistency
    0.40
     Lithuanian
    0.38
     석
    0.37
     কথার
    0.36
     Greek
    0.36
     Lithuania
    0.36
     greek
    0.36
    Greek
    0.35
     गौतम
    0.35
     Consistency
    0.35
    POSITIVE LOGITS
    ᱹ
    0.38
    ષ્ય
    0.38
     Huan
    0.37
    もち
    0.37
    bad
    0.36
    ąda
    0.36
    ভা
    0.36
     Tae
    0.36
     açık
    0.36
    ineed
    0.36
    Activations Density 0.002%

    No Known Activations