© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125905
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    铊
    0.41
     የእ
    0.40
    둰
    0.39
    गीय
    0.39
     difund
    0.38
    кци
    0.37
    ammable
    0.37
    ckte
    0.37
    厘
    0.36
     propag
    0.36
    POSITIVE LOGITS
    feld
    0.38
     DOC
    0.38
    自觉
    0.37
     lot
    0.36
    bid
    0.36
     world
    0.35
     girl
    0.35
     bid
    0.34
    હિ
    0.34
    ”(
    0.34
    Activations Density 0.000%

    No Known Activations