© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93252
    Prev
    Next
    INDEX
    Explanations

    football managers and players

    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_11_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
    tti
    0.58
     దృష్టి
    0.54
    screening
    0.54
     शी
    0.52
    ti
    0.51
    𝐭
    0.51
    skills
    0.50
    ውን
    0.50
    maxn
    0.50
    tiers
    0.50
    POSITIVE LOGITS
    もの
    0.54
     보니
    0.53
     मुस्लिमों
    0.52
    --
    0.52
    Muslim
    0.51
     момент
    0.50
     Lage
    0.50
    +
    0.50
    ৩০
    0.50
     মুহূর্তে
    0.49
    Activations Density 0.000%

    No Known Activations