© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1985
    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
    en
    3.27
     fleste
    3.23
    ت
    2.86
     superconductors
    2.69
     pearls
    2.64
    𝒖
    2.56
    wolves
    2.51
     seguintes
    2.49
    𝒄
    2.49
    تان
    2.46
    POSITIVE LOGITS
    <bos>
    2.57
    nosti
    2.53
    л
    2.44
    iaire
    2.43
    AlertDialog
    2.40
     हूं
    2.30
     κόσ
    2.30
    ructure
    2.27
    hood
    2.15
    hesis
    2.12
    Activations Density 0.359%

    No Known Activations