© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83372
    Prev
    Next
    INDEX
    Explanations

    puppeteer code generation

    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_29_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
    ريع
    0.46
    ந்திர
    0.39
     గౌ
    0.38
     राहणार
    0.38
     حوالي
    0.38
    CLES
    0.38
    賤
    0.37
    𒌆
    0.37
     androgen
    0.36
     carbono
    0.36
    POSITIVE LOGITS
    继续
    0.40
     Wizard
    0.39
     继续
    0.39
     INCREASE
    0.39
    continue
    0.38
     продовжу
    0.38
    wizard
    0.38
     continue
    0.36
     pokrač
    0.35
    Zv
    0.35
    Activations Density 0.004%

    No Known Activations