© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8470
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    {}'.
    3.91
    {}".
    3.70
     bộ
    2.95
    al
    2.94
    et
    2.78
    {}",
    2.76
    и
    2.75
    ۰
    2.70
    clusion
    2.67
    कोर्ट
    2.60
    POSITIVE LOGITS
    zeitig
    2.72
    '_
    2.71
    MSFontService
    2.62
    Bismillahirrah
    2.61
    μη
    2.57
    忡
    2.48
    -_
    2.44
    \{-\
    2.44
    वय
    2.42
    یہ
    2.38
    Activations Density 0.182%

    No Known Activations