© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97701
    Prev
    Next
    INDEX
    Explanations

    requiring all/payment/lenders/businesses/platforms

    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_14_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
    ata
    0.56
     بلغ
    0.54
     lati
    0.54
    rw
    0.47
    ati
    0.46
    si
    0.46
     والتي
    0.45
    뺨
    0.45
    na
    0.44
    ates
    0.44
    POSITIVE LOGITS
    個
    0.57
     Planned
    0.52
    運営
    0.51
    Planned
    0.50
    급
    0.50
    々は
    0.49
    種類
    0.49
    產品
    0.47
    種類の
    0.47
    精彩
    0.47
    Activations Density 0.005%

    No Known Activations