© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2960
    Prev
    Next
    INDEX
    Explanations

    presidents and athletes

    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_5_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
    ../
    1.69
    .'”
    1.69
    }");
    1.68
    ش
    1.66
     власти
    1.65
    to
    1.63
    و
    1.56
    ले
    1.55
    ל
    1.47
     הרב
    1.46
    POSITIVE LOGITS
    hearts
    1.74
    CY
    1.72
    愎
    1.68
    SHIP
    1.66
    MVP
    1.62
    𝗺
    1.62
    𝙥
    1.59
    𝚙
    1.56
    DTO
    1.55
    𝐪
    1.54
    Activations Density 0.019%

    No Known Activations