© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199751
    Prev
    Next
    INDEX
    Explanations

    backed by noun phrase

    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_12_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
     DJI
    0.49
    р
    0.48
     、
    0.48
    悎
    0.47
    صه
    0.46
     hypothalamic
    0.46
     by
    0.45
    ست
    0.45
     Merc
    0.45
    编码
    0.45
    POSITIVE LOGITS
    falen
    0.52
    <0xB5>
    0.51
    soldiers
    0.50
    south
    0.49
    Quality
    0.48
    Six
    0.46
    riol
    0.46
    riots
    0.46
    Orlando
    0.46
    owego
    0.46
    Activations Density 0.001%

    No Known Activations