© 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. 140936
    Prev
    Next
    INDEX
    Explanations

    impressive results or libraries

    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
     {
    0.66
    this
    0.61
     `
    0.61
    ism
    0.59
    author
    0.57
    voice
    0.57
    code
    0.57
    left
    0.56
    password
    0.55
    D
    0.55
    POSITIVE LOGITS
    Pharmaceutical
    0.61
     Матери
    0.57
    Ბ
    0.57
     Нача
    0.55
    ﻙ
    0.55
     diferentes
    0.55
     Даже
    0.54
    合法
    0.54
    椁
    0.54
    UE
    0.53
    Activations Density 0.000%

    No Known Activations