© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52595
    Prev
    Next
    INDEX
    Explanations

    developed by or created by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
     standstill
    0.38
     poise
    0.38
     മന്ത്രി
    0.38
     বিপ
    0.38
    ebly
    0.37
     딱
    0.37
     exactly
    0.36
     begs
    0.36
     obscurity
    0.36
     plenty
    0.36
    POSITIVE LOGITS
    ឆ្ល
    0.39
    intero
    0.38
     século
    0.38
    牛
    0.38
    formData
    0.37
    checking
    0.37
     desenvolvido
    0.37
     polyhedron
    0.36
     desarrollada
    0.36
    usahaan
    0.36
    Activations Density 0.022%

    No Known Activations