© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89467
    Prev
    Next
    INDEX
    Explanations

    low profile. keeps people busy

    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
    ای
    0.85
    on
    0.75
    ي
    0.68
    ве
    0.65
    نس
    0.64
    i
    0.64
    اب
    0.62
    يد
    0.61
    وح
    0.61
    AV
    0.60
    POSITIVE LOGITS
     р
    0.63
     αν
    0.63
     அதனால்
    0.62
     הכ
    0.59
    )."
    0.58
     meille
    0.57
    ).
    0.57
     ismer
    0.56
    atlar
    0.56
     δ
    0.55
    Activations Density 0.000%

    No Known Activations