© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64863
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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_41_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
    Â
    0.38
     Chord
    0.37
    Ę
    0.36
    २०
    0.36
    adav
    0.35
    %.
    0.35
     deem
    0.34
     Brill
    0.34
    ľov
    0.34
     ht
    0.34
    POSITIVE LOGITS
     lemonade
    0.37
    ⣶
    0.37
     ...)
    0.37
     pid
    0.36
    渡
    0.36
    ObjectClass
    0.36
    LinkId
    0.36
     !***
    0.35
    慈
    0.35
     ...(
    0.35
    Activations Density 0.007%

    No Known Activations