© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    on

    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
     Orphans
    0.48
    慳
    0.47
    त्रेयी
    0.47
    /
    0.47
     inmates
    0.46
     Institutes
    0.46
     Ages
    0.46
    काने
    0.45
    SplitContainer
    0.44
     कवाय
    0.44
    POSITIVE LOGITS
     utiliz
    0.49
     მომ
    0.45
     consideramos
    0.45
     unused
    0.45
    𝓌
    0.45
     additional
    0.45
     getKey
    0.45
    specifiedByURL
    0.45
    。）
    0.45
     فلسطين
    0.45
    Activations Density 0.004%

    No Known Activations