© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1508
    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
     vicious
    1.72
     лица
    1.70
    NSNumber
    1.66
    TrackAngle
    1.59
     скорее
    1.56
    +](=
    1.56
    izações
    1.56
     pancreas
    1.52
    𝐨
    1.52
     kej
    1.50
    POSITIVE LOGITS
    y
    2.35
    й
    2.13
    in
    2.07
    م
    1.83
    yed
    1.82
    ので
    1.76
    ka
    1.70
    йки
    1.70
     두고
    1.70
    fring
    1.69
    Activations Density 0.006%

    No Known Activations