© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1409
    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_12_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
     refrained
    0.73
    .")]
    0.72
     along
    0.71
    äum
    0.71
     Rabin
    0.69
     opted
    0.68
     resilient
    0.67
    shand
    0.66
    "]')
    0.65
    物
    0.65
    POSITIVE LOGITS
     केल्यानंतर
    0.88
     फाइ
    0.73
     ஆனால்
    0.71
     लेकिन
    0.71
     वह
    0.70
     ugyan
    0.70
     यह
    0.70
    ऑनलाइन
    0.69
     કર્યો
    0.69
    니까
    0.69
    Activations Density 0.000%

    No Known Activations