© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14474
    Prev
    Next
    INDEX
    Explanations

    validation, lens, testing, bounce

    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_13_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
    >",
    0.46
     flare
    0.41
    덬
    0.39
     dve
    0.38
     lounge
    0.37
    v
    0.37
     adhes
    0.37
     gedaan
    0.37
    ሱን
    0.37
     adhesive
    0.36
    POSITIVE LOGITS
     JACKSON
    0.42
    '
    0.41
    ก
    0.39
    Permission
    0.38
    Eyes
    0.38
    Password
    0.37
    Thankfully
    0.37
    传感器
    0.37
    лда
    0.37
    BackendAuth
    0.37
    Activations Density 0.096%

    No Known Activations