© 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. 6915
    Prev
    Next
    INDEX
    Explanations

    side

    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
     ś
    0.58
     excuse
    0.56
    ilde
    0.52
     squir
    0.51
     muu
    0.51
    𝗆
    0.51
    아요
    0.51
     paga
    0.50
     яка
    0.49
     fum
    0.48
    POSITIVE LOGITS
    ième
    0.59
    esimo
    0.57
    ről
    0.56
    ჯგუფი
    0.54
    wards
    0.53
    deki
    0.53
    ERSON
    0.52
    🧍
    0.52
    laces
    0.51
    िश्वत
    0.51
    Activations Density 0.117%

    No Known Activations