© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142956
    Prev
    Next
    INDEX
    Explanations

    Yes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     가면
    0.40
     нее
    0.39
    फल
    0.38
     XIX
    0.38
    ebel
    0.38
    _",
    0.38
     interlayer
    0.37
    Pack
    0.36
     बनाने
    0.36
    chelon
    0.36
    POSITIVE LOGITS
     determination
    0.42
    ົ
    0.40
    क्रम
    0.40
    determination
    0.39
    امر
    0.38
    真實
    0.38
    perity
    0.38
    真实
    0.37
    COUNTS
    0.37
     lcd
    0.35
    Activations Density 0.006%

    No Known Activations