© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85963
    Prev
    Next
    INDEX
    Explanations

    owner-manager self-interest

    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_3_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
    ü
    0.83
    ة
    0.75
    og
    0.67
    ı
    0.65
    ires
    0.63
    ia
    0.61
    ing
    0.59
    ami
    0.58
    ى
    0.58
     bạn
    0.57
    POSITIVE LOGITS
    t
    0.66
    doesn
    0.59
    зера
    0.54
    ן
    0.54
    אן
    0.54
    resu
    0.54
    itemID
    0.53
    Indirect
    0.52
     हिंदुस्तान
    0.52
    amah
    0.52
    Activations Density 0.001%

    No Known Activations