© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2575
    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_2_width_16k_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
    ㇂
    2.97
    ths
    2.76
     phép
    2.70
    んと
    2.69
    ۣ
    2.68
    需要
    2.63
    តែ
    2.61
    copter
    2.55
     угла
    2.52
     соединения
    2.51
    POSITIVE LOGITS
    ate
    3.49
    კის
    2.75
    р
    2.48
    yay
    2.46
     powerless
    2.30
    мия
    2.30
    yanka
    2.28
    yth
    2.27
    ção
    2.27
    y
    2.27
    Activations Density 0.047%

    No Known Activations