© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48988
    Prev
    Next
    INDEX
    Explanations

    wild animals and conservation

    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_10_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
    (
    0.42
    Blockchain
    0.35
    Aircraft
    0.35
    Xiaomi
    0.34
    PPS
    0.34
    щих
    0.34
    Oste
    0.33
    Schw
    0.33
    ASTM
    0.33
    С
    0.32
    POSITIVE LOGITS
     safari
    0.41
     Safari
    0.38
     African
    0.36
    apore
    0.35
    ’
    0.34
     leopard
    0.34
     Nairobi
    0.34
     antara
    0.34
     Serengeti
    0.33
     Edinburgh
    0.33
    Activations Density 0.029%

    No Known Activations