© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14858
    Prev
    Next
    INDEX
    Explanations

    top, bottom, tail, bar, header

    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_15_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
    <0x9E>
    0.15
     sowohl
    0.15
     pobl
    0.14
     canisters
    0.14
    ő
    0.14
    নব
    0.14
    Earlier
    0.14
    Multicolored
    0.14
    Statement
    0.14
     Azerbaijani
    0.13
    POSITIVE LOGITS
    鷗
    0.18
    瀧
    0.18
    ̣c
    0.17
     дела
    0.17
     мнение
    0.17
    пление
    0.17
    ruction
    0.16
     રહ
    0.16
     facilitating
    0.16
    物流
    0.16
    Activations Density 0.028%

    No Known Activations