© 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. 199819
    Prev
    Next
    INDEX
    Explanations

    explanation of design decisions

    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
    чә
    0.45
     amounted
    0.45
    کات
    0.43
    ,$$
    0.43
    ウム
    0.42
     umo
    0.42
    し
    0.42
     evaluated
    0.42
    вам
    0.41
     Bypass
    0.41
    POSITIVE LOGITS
    el
    0.55
    馊
    0.53
    "})
    0.52
     दशमलव
    0.49
    etting
    0.49
     საბ
    0.48
     தாய்
    0.48
     गरीबी
    0.47
    languages
    0.46
     Inf
    0.45
    Activations Density 0.000%

    No Known Activations