© 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. 17530
    Prev
    Next
    INDEX
    Explanations

    **The explanation of the neuron's behavior is: "push or pull"**

    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
    s
    0.62
    ﺹ
    0.49
     înt
    0.48
    ם
    0.47
     indemnity
    0.47
     ise
    0.47
     במ
    0.46
     deu
    0.46
     עצ
    0.46
     venire
    0.45
    POSITIVE LOGITS
    妹
    0.47
    轭
    0.46
    私募
    0.46
    ங்கி
    0.45
    旋转
    0.45
    Jakarta
    0.45
    द्योगिक
    0.45
     versionName
    0.44
    Про
    0.44
    Stories
    0.44
    Activations Density 0.000%

    No Known Activations