© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210331
    Prev
    Next
    INDEX
    Explanations

    colors like red, blue, or orange

    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_20_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
    連合
    0.45
     privat
    0.42
     brighten
    0.42
    धारी
    0.41
    <b>
    0.40
     ফাঁ
    0.40
     Prins
    0.39
     an
    0.39
     X
    0.39
    一起
    0.39
    POSITIVE LOGITS
     odour
    0.49
     உலக
    0.46
    馄
    0.46
     maíz
    0.46
     अराउंड
    0.45
    谦
    0.44
     milled
    0.43
     moody
    0.43
     Gelände
    0.43
     உணர
    0.42
    Activations Density 0.001%

    No Known Activations