© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196343
    Prev
    Next
    INDEX
    Explanations

    method definitions `def`

    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_27_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
     씨
    0.40
     wc
    0.37
     sofr
    0.36
     completions
    0.35
    的总
    0.35
    ிர்
    0.34
    🚍
    0.34
     uc
    0.34
    两种
    0.33
     thêm
    0.33
    POSITIVE LOGITS
    ภาพ
    0.39
    CompliancePolicy
    0.39
    onie
    0.38
    weeney
    0.38
    ómica
    0.36
    ómicos
    0.36
    itivos
    0.36
     overlying
    0.35
    发挥
    0.35
    ᚐ
    0.35
    Activations Density 0.001%

    No Known Activations