© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194449
    Prev
    Next
    INDEX
    Explanations

    coastal areas and river mouths

    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
    ServiceClient
    0.50
    painting
    0.49
    eeper
    0.49
    SU
    0.48
     ها
    0.48
     blancas
    0.47
     ض
    0.47
    uyentes
    0.46
    舞
    0.46
    春
    0.46
    POSITIVE LOGITS
     eğer
    0.57
     gerçekleş
    0.57
     इंग्लंड
    0.55
     Eğer
    0.55
    grö
    0.54
     attentions
    0.54
     المعادله
    0.54
     Hearing
    0.53
     Thyroid
    0.53
    เมื่อ
    0.52
    Activations Density 0.000%

    No Known Activations