© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4723
    Prev
    Next
    INDEX
    Explanations

    vercel deployment account

    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
    ik
    1.36
    น์
    1.29
    ਾ
    1.21
    ка
    1.21
    ే
    1.19
    ic
    1.14
     benef
    1.12
    ই
    1.11
    از
    1.11
    ურთი
    1.09
    POSITIVE LOGITS
     fact
    1.37
    '%
    1.33
    𝘁
    1.32
    н
    1.22
    s
    1.21
    cknowled
    1.21
    ਆਂ
    1.21
    sender
    1.17
    sellers
    1.16
     ages
    1.13
    Activations Density 0.001%

    No Known Activations