© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16971
    Prev
    Next
    INDEX
    Explanations

    blue whale

    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_15_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
     свет
    0.56
     apresenta
    0.56
     continúa
    0.55
     différente
    0.55
     черно
    0.55
     составляют
    0.55
     другой
    0.53
    ி
    0.53
     цвета
    0.52
     делает
    0.52
    POSITIVE LOGITS
    셨
    0.50
    EndX
    0.48
     ng
    0.47
    োদিত
    0.47
    Ent
    0.46
     Medvedev
    0.46
    成熟
    0.46
    allOf
    0.46
    *
    0.46
    鲔
    0.46
    Activations Density 0.002%

    No Known Activations