© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34694
    Prev
    Next
    INDEX
    Explanations

    electrical components and systems fuse

    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_31_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
    ͞
    0.41
    リル
    0.38
     Invoke
    0.38
     Parnell
    0.38
    лий
    0.38
    рожден
    0.38
    invoke
    0.38
    Parm
    0.37
    DRA
    0.37
     Cas
    0.36
    POSITIVE LOGITS
     cathodic
    0.40
     mediocre
    0.40
    mUserManager
    0.40
     glycol
    0.38
     arg
    0.38
     hypoxic
    0.38
    兖
    0.38
     bandwagon
    0.38
     fusible
    0.38
     defensive
    0.37
    Activations Density 0.031%

    No Known Activations