© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3840
    Prev
    Next
    INDEX
    Explanations

    ambiguity

    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_40_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
    Brent
    0.38
    茵
    0.38
    䨘
    0.37
    㣱
    0.37
     Nike
    0.36
    Nike
    0.35
    振動
    0.35
    㪇
    0.35
    Paul
    0.35
     Ferrari
    0.35
    POSITIVE LOGITS
     ambiguity
    2.69
     ambiguous
    2.56
     ambiguities
    2.47
     Amb
    2.22
     ambigu
    2.20
    Amb
    2.11
     amb
    2.00
    amb
    1.96
     disamb
    1.84
     unambiguous
    1.73
    Activations Density 0.361%

    No Known Activations