© 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. 18027
    Prev
    Next
    INDEX
    Explanations

    attached files

    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
    Us
    0.51
     online
    0.48
    ডার
    0.46
    Use
    0.46
    Chad
    0.46
     White
    0.45
    ዴ
    0.45
    靴
    0.44
     Pro
    0.44
     Online
    0.44
    POSITIVE LOGITS
     ලැබේ
    0.62
    ₁.
    0.57
    ープ
    0.56
     restores
    0.55
    ։
    0.52
    .\
    0.51
    /.
    0.51
     nagu
    0.51
     ハンド
    0.50
    ării
    0.50
    Activations Density 0.002%

    No Known Activations