© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149872
    Prev
    Next
    INDEX
    Explanations

    J

    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_59_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
     turt
    0.39
     형
    0.36
     gat
    0.36
     cak
    0.36
     pence
    0.35
     Tort
    0.35
    ж
    0.35
    ี
    0.35
     doz
    0.35
     turtleneck
    0.35
    POSITIVE LOGITS
    हिणी
    0.40
    awning
    0.40
    ക്കായി
    0.40
    Ⲁ
    0.40
    uchtigkeit
    0.38
    忶
    0.38
    Lst
    0.37
    ள்ளன
    0.36
    ዎት
    0.36
    Bolt
    0.35
    Activations Density 0.000%

    No Known Activations