© 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. 2587
    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
    ్వ
    2.19
     desire
    1.99
     [];
    1.95
     Desire
    1.93
     poč
    1.84
    栻
    1.81
    cropped
    1.80
     arrivée
    1.78
    ivity
    1.77
    骜
    1.76
    POSITIVE LOGITS
    াল
    1.97
    드
    1.93
     đỡ
    1.71
    бна
    1.69
    cısı
    1.63
    fully
    1.59
    드를
    1.58
     Rohit
    1.57
    desk
    1.55
     fath
    1.53
    Activations Density 0.233%

    No Known Activations