© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6420
    Prev
    Next
    INDEX
    Explanations

    decoding model outputs

    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_40_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
    브
    0.33
    聯合
    0.33
     কম্পিউ
    0.31
     divulge
    0.31
     компью
    0.31
     beginner
    0.31
    ワーク
    0.30
     Immune
    0.30
     против
    0.30
    ᵍ
    0.30
    POSITIVE LOGITS
     पीढ़ी
    0.34
     Pec
    0.34
     Reis
    0.33
     Comes
    0.33
    ieder
    0.32
    Johnny
    0.32
     Johanna
    0.31
     आया
    0.30
    came
    0.30
    May
    0.30
    Activations Density 0.003%

    No Known Activations