© 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. 8573
    Prev
    Next
    INDEX
    Explanations

    in + [word starting with 'se', 'ju', 'cr', 'br', 've', 'ef', 'co', 'la', 'ha']

    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
    é
    1.08
    лива
    1.00
    啉
    0.94
    ли
    0.94
    ia
    0.91
     diante
    0.91
    чет
    0.90
     وقد
    0.89
    dri
    0.89
    c
    0.88
    POSITIVE LOGITS
    ために
    1.25
    ो
    1.23
    我
    1.17
    م
    1.13
    espa
    1.07
    tedir
    1.06
    Очень
    1.00
    我也是
    0.99
     rites
    0.99
    mselves
    0.98
    Activations Density 0.031%

    No Known Activations