© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81403
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
    abca
    0.46
    ǚ
    0.39
     craftsmen
    0.37
     casket
    0.36
     suck
    0.36
     cerv
    0.36
     meny
    0.35
    breadcrumb
    0.35
     cel
    0.35
     souh
    0.35
    POSITIVE LOGITS
    충
    0.43
     після
    0.37
     운동
    0.37
    䤃
    0.37
     충
    0.37
     אחרי
    0.36
     призначення
    0.36
    联系
    0.35
    운동
    0.34
     iterated
    0.34
    Activations Density 0.032%

    No Known Activations