© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15588
    Prev
    Next
    INDEX
    Explanations

    Here's the explanation for the neuron's behavior:information, identity, policy

    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_15_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
    /
    0.43
    ili
    0.40
     (
    0.39
     fric
    0.38
    ole
    0.38
    0.37
    angs
    0.37
    oles
    0.36
    és
    0.36
    oco
    0.36
    POSITIVE LOGITS
    訣
    0.41
     mengungkap
    0.41
     صارفین
    0.41
     Queries
    0.40
     свого
    0.40
     queries
    0.39
     與
    0.39
     방
    0.39
     చెప్పారు
    0.39
     své
    0.38
    Activations Density 0.026%

    No Known Activations