© 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. 158795
    Prev
    Next
    INDEX
    Explanations

    names closet

    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
    Syn
    0.41
     С
    0.41
     Cuff
    0.40
    ニコ
    0.40
     impot
    0.39
    ज्
    0.39
    С
    0.38
    Pascal
    0.37
     Synchron
    0.37
    C
    0.37
    POSITIVE LOGITS
    ibert
    0.44
     Josh
    0.39
     closet
    0.36
     muebles
    0.36
    ὸς
    0.36
    墜
    0.35
    Josh
    0.35
     Bernie
    0.35
     Closet
    0.35
     illustrator
    0.35
    Activations Density 0.000%

    No Known Activations