© 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. 7520
    Prev
    Next
    INDEX
    Explanations

    funnel

    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
    ংলার
    1.66
    ява
    1.62
    anut
    1.58
     potatoes
    1.56
    в
    1.56
    ్ఞ
    1.55
    లుగు
    1.55
     incurred
    1.53
     overcome
    1.51
     fashioned
    1.51
    POSITIVE LOGITS
    Sincerely
    1.88
    𝐓
    1.86
    Xem
    1.76
    𝐠
    1.75
    𝐜
    1.74
    𝐡
    1.72
    𝐫
    1.69
    𝐭
    1.66
    𝐑
    1.65
     snad
    1.61
    Activations Density 0.002%

    No Known Activations