© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210865
    Prev
    Next
    INDEX
    Explanations

    words starting with dis

    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_5_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
    azione
    1.01
    L
    1.00
    ulation
    0.95
    lijk
    0.95
    bergs
    0.93
    apeut
    0.92
    M
    0.91
    hearted
    0.91
    foration
    0.90
    brechen
    0.90
    POSITIVE LOGITS
    i
    1.58
    u
    1.52
    ي
    1.49
    ু
    1.49
    ט
    1.49
    q
    1.43
    in
    1.39
    ות
    1.38
    e
    1.36
    é
    1.36
    Activations Density 0.000%

    No Known Activations