© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144366
    Prev
    Next
    INDEX
    Explanations

    exclude things

    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_0_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
     critic
    1.28
     for
    1.26
    س
    1.24
    什么
    1.23
     moistur
    1.23
     restaur
    1.21
    ts
    1.20
    的技术
    1.20
     expon
    1.20
     uuid
    1.15
    POSITIVE LOGITS
     cataly
    1.14
    ভ
    1.14
    uksen
    1.08
    ната
    1.05
    1.02
    im
    1.02
    गंज
    0.98
    amaya
    0.95
     svært
    0.93
    не
    0.93
    Activations Density 0.000%

    No Known Activations