© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 164540
    Prev
    Next
    INDEX
    Explanations

    stone and rock

    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
    物
    0.39
     вода
    0.37
     물
    0.35
    Wasser
    0.35
    热水
    0.35
    水分
    0.33
    paran
    0.33
    云
    0.33
    WATER
    0.32
     Bauern
    0.32
    POSITIVE LOGITS
    მიან
    0.39
     livers
    0.38
     liver
    0.37
     salespeople
    0.36
     ReLU
    0.36
    Restore
    0.36
    Subgraph
    0.36
     suit
    0.34
    Clientes
    0.34
     distributors
    0.34
    Activations Density 0.008%

    No Known Activations