© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256692
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    وْ
    1.27
    ع
    1.27
    й
    1.25
    これ
    1.22
    عند
    1.19
     rada
    1.16
     cristall
    1.15
    اندا
    1.14
    이상
    1.14
     प्रताप
    1.13
    POSITIVE LOGITS
    ujący
    1.19
    ności
    1.07
    īb
    1.06
     يول
    1.06
     adhere
    1.05
    𝐅
    1.04
    ującego
    1.04
    斐
    1.02
    ಪಡ
    1.02
    𝗖
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.