© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260441
    Prev
    Next
    INDEX
    Explanations

    image processing return

    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_22_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
    uating
    0.46
    nada
    0.40
     практику
    0.40
    roomId
    0.38
    iad
    0.37
    沟
    0.37
    DoesNotExist
    0.36
    ાઓ
    0.35
     borrowing
    0.35
     своих
    0.35
    POSITIVE LOGITS
     Louise
    0.39
     bár
    0.39
     Yat
    0.38
     PFC
    0.38
    蒯
    0.38
     Kend
    0.38
     Kendrick
    0.38
    关键
    0.38
     Zuschauer
    0.37
     ساق
    0.37
    Activations Density 0.008%

    No Known Activations