© 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. 259106
    Prev
    Next
    INDEX
    Explanations

    logged in

    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
     fruits
    0.53
    Textbox
    0.52
    fruits
    0.51
    Fruits
    0.47
     Fruits
    0.47
    marsh
    0.46
     Cuthbert
    0.45
    른
    0.44
    fruit
    0.44
     Except
    0.44
    POSITIVE LOGITS
     mencari
    0.67
    𖥔
    0.65
     ori
    0.65
     AAA
    0.64
     अॅ
    0.63
     יש
    0.63
    owania
    0.62
     iga
    0.62
     જાણી
    0.62
    ඇ
    0.61
    Activations Density 0.000%

    No Known Activations