© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51370
    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_31_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
    MRS
    0.41
     Rostov
    0.34
    attro
    0.34
     оцени
    0.34
    视
    0.34
    learning
    0.34
    Spending
    0.34
    portrait
    0.33
    赸
    0.33
     aprendido
    0.33
    POSITIVE LOGITS
     kaf
    0.40
     tying
    0.39
    τια
    0.39
    экономи
    0.38
     keg
    0.37
     hemolysis
    0.37
     hems
    0.37
    rahmen
    0.36
     ekonom
    0.36
     Snackbar
    0.36
    Activations Density 0.000%

    No Known Activations