© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 172310
    Prev
    Next
    INDEX
    Explanations

    August 15th, observed

    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
    വിന്
    0.44
    oppositions
    0.44
    İlk
    0.43
    ovariant
    0.42
    Radians
    0.38
    örder
    0.38
    rodní
    0.38
    瞧
    0.38
    radians
    0.38
    瞟
    0.38
    POSITIVE LOGITS
     silo
    0.47
     funding
    0.46
     store
    0.43
     individual
    0.43
     raise
    0.42
     funders
    0.41
     BO
    0.41
     candy
    0.41
    несен
    0.40
     longevity
    0.40
    Activations Density 0.000%

    No Known Activations