© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217768
    Prev
    Next
    INDEX
    Explanations

    control followed by punctuation or role

    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_16_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
    пра
    0.26
    ר
    0.25
    ر
    0.24
    Butter
    0.23
    Rivers
    0.23
     for
    0.23
    U
    0.23
    （
    0.22
    Pe
    0.21
     Pe
    0.21
    POSITIVE LOGITS
     cloison
    0.25
    зыка
    0.24
    okedex
    0.22
    efeller
    0.22
    izdat
    0.22
     impulsar
    0.21
    ordnet
    0.21
     plantel
    0.21
     चमकदार
    0.21
     विविधता
    0.20
    Activations Density 0.005%

    No Known Activations