© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157862
    Prev
    Next
    INDEX
    Explanations

    academic writing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    𐱅
    0.46
    CreateIndex
    0.39
    Programme
    0.38
    ワクチン
    0.36
     Waik
    0.35
     Keegan
    0.35
    蝿
    0.35
     Keys
    0.35
    뀌
    0.35
    Azur
    0.34
    POSITIVE LOGITS
    viso
    0.41
    紥
    0.41
     piston
    0.40
     ग्लो
    0.38
     MATERIAL
    0.37
     삶
    0.37
    ologist
    0.37
    Cohen
    0.37
    ﺯ
    0.37
    ופ
    0.36
    Activations Density 0.004%

    No Known Activations