© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1831
    Prev
    Next
    INDEX
    Explanations

    house character setting

    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_40_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
     reader
    0.52
     Reader
    0.46
    READER
    0.42
     READER
    0.38
    🚮
    0.38
     Communist
    0.38
     lectores
    0.38
    读者
    0.37
    Reader
    0.37
    吔
    0.36
    POSITIVE LOGITS
    ාල
    0.53
    House
    0.43
     $/
    0.42
    Uber
    0.40
    HOUSE
    0.40
    house
    0.39
     House
    0.38
     जले
    0.38
    Liability
    0.38
     Donnelly
    0.38
    Activations Density 0.055%

    No Known Activations