© 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. 7942
    Prev
    Next
    INDEX
    Explanations

    George, Georgia, Georgian

    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
    ер
    3.97
    之处
    3.02
     bentuk
    2.92
     полномо
    2.90
    これ
    2.72
     hace
    2.71
    ত
    2.71
    ка
    2.69
    érateur
    2.65
     ouvertes
    2.65
    POSITIVE LOGITS
    𝐫
    3.97
    𝐧
    3.68
    𝐞
    3.36
    𝐬
    3.21
    𝐭
    3.20
     gosh
    3.19
    𝐑
    3.18
    𝐍
    3.13
    𝐲
    3.08
    𝐥
    3.04
    Activations Density 0.013%

    No Known Activations