© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7153
    Prev
    Next
    INDEX
    Explanations

    Instagram

    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
    amiento
    1.80
     comprendere
    1.76
    iksaan
    1.65
    hangi
    1.58
    먼
    1.56
     sebepler
    1.55
     fait
    1.54
     capire
    1.50
     cosines
    1.48
    
    1.48
    POSITIVE LOGITS
     dune
    1.81
    ͯ
    1.79
     SDI
    1.72
     dihar
    1.71
     eTo
    1.71
    ␮
    1.71
     silverware
    1.70
    ступ
    1.69
     TLC
    1.69
     ITS
    1.69
    Activations Density 0.048%

    No Known Activations