© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204206
    Prev
    Next
    INDEX
    Explanations

    think

    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_46_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
    得很
    0.39
    NSError
    0.38
    ใหญ่
    0.37
    гам
    0.36
     좋
    0.36
    高于
    0.36
    りたい
    0.36
    ใหญ
    0.35
    gramModel
    0.35
    ffff
    0.35
    POSITIVE LOGITS
    ඟ
    0.39
    蟋
    0.38
     върху
    0.38
    ेशा
    0.38
     caso
    0.37
    positive
    0.37
    క్తి
    0.36
     CASE
    0.35
    नात
    0.35
     Case
    0.35
    Activations Density 0.004%

    No Known Activations