© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164832
    Prev
    Next
    INDEX
    Explanations

    buy low, sell high

    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_13_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
    atives
    0.49
    ir
    0.47
    ك
    0.47
    ص
    0.46
    عهد
    0.45
    ig
    0.43
    閎
    0.43
    كب
    0.42
    ἱ
    0.42
    fu
    0.42
    POSITIVE LOGITS
     Sağ
    0.52
     shop
    0.51
     sağ
    0.50
    Homo
    0.47
     civilized
    0.46
     caramelized
    0.46
    Started
    0.45
     civilization
    0.44
    ने
    0.44
     controller
    0.44
    Activations Density 0.000%

    No Known Activations