© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208741
    Prev
    Next
    INDEX
    Explanations

    local path

    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_20_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
     logics
    0.46
     elm
    0.45
    ysz
    0.44
    莹
    0.43
     telefoon
    0.43
    otos
    0.42
    CAST
    0.42
    erar
    0.41
    铸
    0.41
    建造
    0.40
    POSITIVE LOGITS
     čega
    0.42
     Efforts
    0.42
    ương
    0.41
     Conditional
    0.41
     वै
    0.41
     Encourage
    0.41
     Recognized
    0.41
     oper
    0.41
     सहयोगी
    0.41
     Aug
    0.40
    Activations Density 0.002%

    No Known Activations