© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197126
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    쿄
    0.39
    랗
    0.39
     মাইক্র
    0.39
     싸
    0.38
    ビング
    0.38
    Bing
    0.38
    甚
    0.38
     расти
    0.38
    jsdel
    0.38
     пошу
    0.38
    POSITIVE LOGITS
     ragged
    0.44
     family
    0.40
    ct
    0.39
     amalgamated
    0.39
     £
    0.38
     butter
    0.38
     jagged
    0.38
     R
    0.38
     alienated
    0.38
     deviated
    0.38
    Activations Density 0.000%

    No Known Activations