© 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. 102486
    Prev
    Next
    INDEX
    Explanations

    Node.js

    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
    v
    0.57
    ik
    0.50
    j
    0.50
     deviennent
    0.47
    ៕
    0.46
    k
    0.46
    اين
    0.46
    ”。
    0.45
    блю
    0.45
    к
    0.45
    POSITIVE LOGITS
     רק
    0.55
     bans
    0.54
     unsur
    0.51
     upon
    0.50
     udara
    0.50
     учета
    0.49
    IES
    0.49
     usk
    0.48
     only
    0.48
     Hana
    0.47
    Activations Density 0.006%

    No Known Activations