© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61831
    Prev
    Next
    INDEX
    Explanations

    bodies of water

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     мо
    1.52
     ha
    1.15
     mor
    1.00
     바
    0.82
     Mor
    0.80
    mor
    0.78
     mô
    0.76
    Mor
    0.75
    바
    0.73
     mora
    0.73
    POSITIVE LOGITS
     sea
    2.02
     Sea
    1.63
    Sea
    1.63
    sea
    1.53
     ocean
    1.15
    海
    1.15
     море
    0.98
     seja
    0.96
     Ocean
    0.95
    Ocean
    0.89
    Activations Density 0.019%

    No Known Activations