© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 238949
    Prev
    Next
    INDEX
    Explanations

    array indices

    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_25_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
    ကျော်
    0.39
     espécies
    0.38
    ധ്യമ
    0.36
    pecies
    0.35
     especies
    0.35
    usia
    0.35
     Instruct
    0.34
    접
    0.34
    asion
    0.34
    RENCE
    0.34
    POSITIVE LOGITS
     phenyl
    0.46
    Phenyl
    0.42
    影片
    0.38
    Ca
    0.38
     pengambilan
    0.38
     Doppel
    0.37
     Charcoal
    0.37
     Anthem
    0.36
     Wast
    0.36
     charcoal
    0.35
    Activations Density 0.001%

    No Known Activations