© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49958
    Prev
    Next
    INDEX
    Explanations

    un + word, negation or prefix

    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_10_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
    ет
    0.98
     lahko
    0.86
    า
    0.85
     από
    0.84
     órdenes
    0.84
     ήταν
    0.82
    ことなく
    0.82
     Từ
    0.79
     pequeña
    0.78
     seves
    0.78
    POSITIVE LOGITS
    i
    1.13
    mi
    0.87
    ij
    0.86
    ي
    0.85
    mu
    0.84
    y
    0.83
    den
    0.83
    da
    0.81
    ds
    0.81
    der
    0.80
    Activations Density 0.021%

    No Known Activations