© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123919
    Prev
    Next
    INDEX
    Explanations

    pronunciation and comprehension of sounds/words

    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_37_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
     read
    1.76
     읽
    1.72
     reading
    1.70
     đọc
    1.63
    读
    1.62
    읽
    1.58
     reads
    1.57
    read
    1.52
    読み
    1.52
     membaca
    1.52
    POSITIVE LOGITS
    strconv
    0.36
    Reach
    0.36
    到了
    0.36
    }=(-
    0.35
    にあ
    0.34
     termos
    0.33
    Стро
    0.33
    最具
    0.33
     next
    0.32
     reach
    0.32
    Activations Density 0.028%

    No Known Activations