© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12198
    Prev
    Next
    INDEX
    Explanations

    piston engine components

    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_13_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
    ará
    0.46
    விரி
    0.44
    可能会
    0.44
     manic
    0.44
    L
    0.44
    leti
    0.43
     hará
    0.43
     cor
    0.43
    usti
    0.42
    cor
    0.42
    POSITIVE LOGITS
     Prozent
    0.53
     Routes
    0.52
     Königreich
    0.51
     Ferien
    0.50
     Employment
    0.50
     ciências
    0.49
    িলারা
    0.48
     %(
    0.47
    ousel
    0.47
     sciences
    0.47
    Activations Density 0.007%

    No Known Activations