© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42531
    Prev
    Next
    INDEX
    Explanations

    Nordic countries and regions

    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
    Ⲧ
    0.14
    ➫
    0.13
    Ⴀ
    0.13
    海の
    0.12
    𝐴
    0.12
    лянчук
    0.12
     TIMES
    0.12
     Danmark
    0.12
    𝑇
    0.12
    मूलन
    0.12
    POSITIVE LOGITS
    is
    0.14
    }
    0.13
    ides
    0.12
    et
    0.12
    ant
    0.12
    ase
    0.12
    ak
    0.12
    ij
    0.12
    as
    0.12
    esley
    0.12
    Activations Density 0.002%

    No Known Activations