© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202763
    Prev
    Next
    INDEX
    Explanations

    gorges

    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_37_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
    redi
    0.44
     કરવું
    0.39
    řich
    0.38
     nokta
    0.38
    ائش
    0.36
    皖
    0.36
    flashdata
    0.36
    collar
    0.36
    devel
    0.36
    ライズ
    0.36
    POSITIVE LOGITS
     Sam
    0.38
    AGT
    0.38
     plate
    0.38
    阻
    0.37
     그리
    0.37
    Graph
    0.36
     Hopefully
    0.36
    hej
    0.36
     [-
    0.35
     Was
    0.35
    Activations Density 0.001%

    No Known Activations