© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9548
    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_25_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
     सुधार
    0.64
    ިން
    0.60
    වත
    0.57
    ปฏิ
    0.57
     संबंध
    0.57
     saç
    0.56
    exit
    0.56
    祇
    0.55
     Yum
    0.55
     mMediaPlayer
    0.54
    POSITIVE LOGITS
     mobil
    2.24
     Mobil
    2.23
    Mobil
    2.21
     mobilization
    2.09
     mobilized
    2.07
     mobilize
    2.04
    mobil
    2.02
     mobilizing
    1.96
     deployment
    1.93
     deploy
    1.92
    Activations Density 0.329%

    No Known Activations