© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80202
    Prev
    Next
    INDEX
    Explanations

    Mo prefix

    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_53_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
    Her
    0.38
     সম
    0.37
    Gates
    0.36
     lipid
    0.36
    stens
    0.35
     Her
    0.35
    sten
    0.34
    石
    0.34
    stones
    0.34
    ajib
    0.34
    POSITIVE LOGITS
     Jerome
    0.39
    ulators
    0.38
     PRODUCT
    0.38
     Carroll
    0.37
    ició
    0.37
    KindOfClass
    0.37
    ciples
    0.37
    undas
    0.36
     sétimo
    0.36
     ረ
    0.36
    Activations Density 0.001%

    No Known Activations