© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93370
    Prev
    Next
    INDEX
    Explanations

    erosion control, hay

    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_11_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
     washing
    0.54
     fringe
    0.51
     methylation
    0.51
     messenger
    0.48
     d
    0.48
     shells
    0.48
     methyl
    0.46
    navigate
    0.46
    ление
    0.46
    flare
    0.46
    POSITIVE LOGITS
    א
    0.60
    Ș
    0.56
    માં
    0.55
     ReturnVal
    0.55
    ווי
    0.55
     Melhor
    0.54
     Moines
    0.53
    Debut
    0.53
    Გ
    0.53
    ik
    0.52
    Activations Density 0.002%

    No Known Activations