© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197312
    Prev
    Next
    INDEX
    Explanations

    scale, entropy, and dashboards

    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_15_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
    ലോ
    0.51
    ર્સ
    0.50
    າ
    0.49
     retorn
    0.48
    हून
    0.48
     overjoyed
    0.48
     exhilar
    0.48
    AND
    0.46
    Ꮘ
    0.45
     trazendo
    0.45
    POSITIVE LOGITS
     team
    0.45
     Protein
    0.44
     syn
    0.44
     protein
    0.44
     vision
    0.42
    Binding
    0.42
    behind
    0.41
     }
    0.41
     Provision
    0.40
     Fl
    0.40
    Activations Density 0.000%

    No Known Activations