© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7743
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    柾
    0.43
     നേതാ
    0.41
     Married
    0.40
     proved
    0.39
    投注
    0.38
     экономического
    0.38
    经销商
    0.38
     relinquished
    0.38
    kopp
    0.38
    鏻
    0.38
    POSITIVE LOGITS
    pertino
    0.42
    protect
    0.40
    nin
    0.38
    Had
    0.36
     coming
    0.36
    align
    0.36
     করতেই
    0.36
    ляет
    0.36
    target
    0.35
    pixel
    0.35
    Activations Density 0.000%

    No Known Activations