© 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. 42153
    Prev
    Next
    INDEX
    Explanations

    Decision support systems

    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
    is
    1.15
    ’
    0.94
    to
    0.91
    の前
    0.82
    AG
    0.82
    ang
    0.79
    ’”
    0.76
    ER
    0.75
     Entscheidung
    0.72
     Decide
    0.71
    POSITIVE LOGITS
    ی
    0.74
     in
    0.70
    𝑠
    0.68
    ;
    0.66
    сист
    0.64
    ค์
    0.61
     आपण
    0.61
    {
    0.61
     on
    0.60
     sisi
    0.60
    Activations Density 0.002%

    No Known Activations