© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78356
    Prev
    Next
    INDEX
    Explanations

    football club

    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_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
    headings
    0.35
    缤
    0.35
    ruppe
    0.34
    দৈ
    0.34
     Compass
    0.33
     Capability
    0.33
    战士
    0.33
     odstr
    0.33
    Compass
    0.32
    帳
    0.32
    POSITIVE LOGITS
     clube
    0.64
     klub
    0.56
     clubes
    0.52
     klubu
    0.49
     клуба
    0.48
    クラブ
    0.47
     क्लब
    0.47
     club
    0.47
     clubs
    0.46
    俱乐部
    0.46
    Activations Density 0.006%

    No Known Activations