© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174905
    Prev
    Next
    INDEX
    Explanations

    copyrighted material

    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_20_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
     improves
    0.50
     strengthens
    0.48
     enhances
    0.48
    由
    0.47
     toujours
    0.47
     childish
    0.47
     threatens
    0.47
     contributes
    0.47
     helps
    0.46
    वाहिक
    0.46
    POSITIVE LOGITS
     pab
    0.43
    )+\
    0.41
    tmpobj
    0.39
     المست
    0.39
    둡
    0.39
    氘
    0.39
    鼻子
    0.38
    zeti
    0.38
    GAP
    0.37
    MCP
    0.37
    Activations Density 0.001%

    No Known Activations