© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    jelly beans

    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
    🅻
    1.60
    ﻣ
    1.54
    eclipse
    1.51
    𝗽
    1.50
    etään
    1.46
     headline
    1.45
     verge
    1.45
    𝟭
    1.44
     glider
    1.44
    𝗿
    1.44
    POSITIVE LOGITS
    ер
    1.62
    েল
    1.46
    яти
    1.44
    lož
    1.41
    वय
    1.41
    ъ
    1.32
     இதனால்
    1.28
    miş
    1.27
    то
    1.27
    ground
    1.25
    Activations Density 0.002%

    No Known Activations