© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32937
    Prev
    Next
    INDEX
    Explanations

    shipping costs, freight, customs, duties

    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_31_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
     چو
    0.39
     appass
    0.37
    羈
    0.37
    বলী
    0.35
     అభిమా
    0.34
     APPLY
    0.34
     खुलकर
    0.33
    าตุ
    0.33
    帷
    0.32
     causas
    0.32
    POSITIVE LOGITS
    诈
    0.40
     strictest
    0.36
     strict
    0.34
     racetr
    0.32
     monet
    0.32
     glab
    0.32
     lemons
    0.32
     scooters
    0.31
     triad
    0.31
     trader
    0.31
    Activations Density 0.015%

    No Known Activations