© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106683
    Prev
    Next
    INDEX
    Explanations

    factual accuracy

    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_1_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
    ج
    1.32
    ق
    1.20
    ب
    1.04
    '
    0.98
    場合
    0.97
    ا
    0.92
     در
    0.90
    아
    0.89
    ست
    0.88
     قد
    0.88
    POSITIVE LOGITS
    AY
    1.23
    UM
    1.20
    E
    1.16
    U
    1.09
    EL
    1.08
    S
    1.07
    ER
    1.06
    I
    1.06
    AB
    1.05
    UN
    1.04
    Activations Density 0.000%

    No Known Activations