© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173256
    Prev
    Next
    INDEX
    Explanations

    UI element names

    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_20_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
     köy
    0.46
    の良い
    0.46
     অভিযুক্ত
    0.45
    🌜
    0.43
     છું
    0.42
     professionale
    0.42
    oretical
    0.42
    很多人
    0.42
    려고
    0.41
     নিযুক্ত
    0.41
    POSITIVE LOGITS
     Radi
    0.48
     radi
    0.45
    Radi
    0.44
    весто
    0.44
     Its
    0.44
     Rent
    0.43
     GAAP
    0.42
     pant
    0.41
    ６
    0.41
     heat
    0.40
    Activations Density 0.000%

    No Known Activations