© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13769
    Prev
    Next
    INDEX
    Explanations

    3D printing filament

    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_15_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
    卫生
    0.60
    вається
    0.56
    نة
    0.52
    ・・
    0.51
    衛生
    0.47
    低
    0.46
    оборот
    0.46
    어를
    0.45
    низ
    0.45
     Liaison
    0.45
    POSITIVE LOGITS
    fh
    0.48
     Yin
    0.48
    の中に
    0.47
     новом
    0.47
     आपकी
    0.47
     fabric
    0.47
     लेन
    0.47
     Y
    0.47
    Dy
    0.47
     দেখো
    0.46
    Activations Density 0.001%

    No Known Activations