© 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. 132041
    Prev
    Next
    INDEX
    Explanations

    government departments

    np_max-act-logits · gemini-2.5-flash-lite
    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
    Inher
    0.41
    Ἥ
    0.37
     เห
    0.37
    Defs
    0.36
     социального
    0.36
     ခု
    0.36
    issé
    0.36
    ၡ
    0.36
    Hig
    0.35
     Haga
    0.35
    POSITIVE LOGITS
    L
    0.55
     L
    0.50
    表達
    0.44
     communities
    0.43
     biennial
    0.42
     Communities
    0.41
    コミュニ
    0.41
    loa
    0.40
     prek
    0.40
     DDT
    0.39
    Activations Density 0.002%

    No Known Activations