© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215274
    Prev
    Next
    INDEX
    Explanations

    supervision

    np_max-act-logits · gemini-2.5-flash-lite

    foreign language text and technical terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @cam
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     sustent
    0.39
    exponent
    0.38
     repell
    0.38
    @[+][
    0.38
    ))){
    0.37
    쏨
    0.37
     Wiener
    0.36
     लैंग्वे
    0.36
    btnLogin
    0.36
    
    0.36
    POSITIVE LOGITS
     supervision
    1.55
    監督
    1.55
     supervis
    1.41
     Supervision
    1.41
     supervise
    1.36
     감독
    1.36
     supervisory
    1.34
     supervising
    1.33
    监督
    1.32
    감독
    1.32
    Activations Density 0.000%

    No Known Activations