© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59421
    Prev
    Next
    INDEX
    Explanations

    thorny issue, equation, or descriptor

    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_11_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
    )
    0.62
    freq
    0.60
    call
    0.58
    ad
    0.57
    yss
    0.56
    b
    0.55
    calls
    0.55
    갱
    0.55
    de
    0.54
    dp
    0.54
    POSITIVE LOGITS
     </
    0.71
     ات
    0.60
     изо
    0.59
    ?»
    0.58
     tarifs
    0.58
     उससे
    0.56
     нескольких
    0.56
     самом
    0.55
    ?</
    0.55
    ె
    0.55
    Activations Density 0.001%

    No Known Activations