© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259118
    Prev
    Next
    INDEX
    Explanations

    installation and assembly

    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_10_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
    .[
    0.83
    ález
    0.82
     immig
    0.82
    .$
    0.80
    .[/
    0.79
     employ
    0.79
    [/
    0.77
    .]
    0.77
    founder
    0.76
    .
    0.75
    POSITIVE LOGITS
     Нет
    0.84
     Zahlen
    0.83
     Ksh
    0.79
    纽约
    0.79
     Geschäft
    0.78
    বার্গ
    0.77
    avalt
    0.77
    ヨーロッパ
    0.76
     Ι
    0.76
    ண்ட
    0.76
    Activations Density 0.001%

    No Known Activations