© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177386
    Prev
    Next
    INDEX
    Explanations

    code blocks and punctuation

    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_24_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
    ต้
    0.57
    могою
    0.53
     embarrassment
    0.50
    ванта
    0.50
     disgrace
    0.50
     имена
    0.48
    ת
    0.48
    ними
    0.47
    ナンバー
    0.46
    ﹞
    0.46
    POSITIVE LOGITS
    AW
    0.43
     تاريخ
    0.42
     rendezvous
    0.42
    ReactDOM
    0.41
    argento
    0.41
     داد
    0.41
    ÃO
    0.40
     Finch
    0.39
     Gillette
    0.39
    addSprite
    0.39
    Activations Density 0.000%

    No Known Activations