© 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-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6203
    Prev
    Next
    INDEX
    Explanations

    DATE: entries

    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_39_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
     bieg
    0.43
     bifur
    0.38
     Roder
    0.38
     polu
    0.37
     scales
    0.37
     extractor
    0.37
    дино
    0.37
    ")}}'
    0.36
    тности
    0.36
     chests
    0.36
    POSITIVE LOGITS
    ্ঞ
    0.40
     gọn
    0.39
    Immediate
    0.39
    ConfigRequest
    0.38
    riline
    0.37
     Som
    0.37
    Jake
    0.37
    Agr
    0.37
     vess
    0.36
    som
    0.36
    Activations Density 0.005%

    No Known Activations