© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2762
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ת
    3.02
    л
    2.85
    𝘮
    2.77
    𝘨
    2.71
    𝘵
    2.63
    𝘳
    2.57
    т
    2.53
    あれば
    2.45
    н
    2.39
    ة
    2.33
    POSITIVE LOGITS
    檎
    2.68
    ى
    2.59
    ्स
    2.49
     blame
    2.42
    ModelAndView
    2.34
    ясь
    2.31
    ɴ
    2.23
    vist
    2.14
     intim
    2.11
    nang
    2.11
    Activations Density 0.019%

    No Known Activations