© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25525
    Prev
    Next
    INDEX
    Explanations

    Atlantic coast and oceans

    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
    k
    0.91
    kst
    0.89
    kta
    0.89
    klin
    0.80
    ة
    0.79
    ma
    0.78
    дно
    0.78
    kten
    0.77
    umers
    0.77
    kyl
    0.77
    POSITIVE LOGITS
     Atlantic
    1.00
    ע
    0.87
     ATL
    0.84
     over
    0.79
    מ
    0.79
     atlantic
    0.79
     de
    0.78
    /
    0.77
    ている
    0.75
     prototyping
    0.75
    Activations Density 0.007%

    No Known Activations