© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31928
    Prev
    Next
    INDEX
    Explanations

    knowledgeable book

    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
     Inclusion
    0.40
     postcode
    0.38
     লাভ
    0.36
     reconfiguration
    0.36
     tái
    0.36
    getCameraId
    0.35
     Topology
    0.35
     ਘ
    0.35
    BrN
    0.34
    Estimation
    0.34
    POSITIVE LOGITS
     chopped
    0.38
     eating
    0.36
     Peoria
    0.35
     wallpaper
    0.33
     entirely
    0.33
     shaved
    0.32
     Eating
    0.32
     talked
    0.32
     aged
    0.32
     keyed
    0.31
    Activations Density 0.002%

    No Known Activations