© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67099
    Prev
    Next
    INDEX
    Explanations

    ancient lost civilization

    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
     magic
    0.43
     Dragon
    0.41
     heathen
    0.41
     Ar
    0.40
     pagan
    0.40
    ointment
    0.39
     dragons
    0.39
    菻
    0.39
     crusade
    0.38
    Troy
    0.38
    POSITIVE LOGITS
    older
    0.37
    kitty
    0.37
    嚿
    0.37
    xm
    0.36
     タン
    0.36
    펄
    0.36
    dot
    0.36
    folded
    0.35
     dispersions
    0.35
    पीडी
    0.35
    Activations Density 0.014%

    No Known Activations