© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11572
    Prev
    Next
    INDEX
    Explanations

    Copernican Revolution

    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_13_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
    isse
    0.13
    ise
    0.12
     ی
    0.12
    ync
    0.12
     waarop
    0.12
    ody
    0.12
     \\
    0.11
    ollowing
    0.11
    ensing
    0.11
    ies
    0.11
    POSITIVE LOGITS
     municipalité
    0.14
     photometric
    0.13
    Smoothing
    0.13
    তীশ
    0.13
     emis
    0.13
     ንጥረ
    0.13
    陨
    0.13
     tedious
    0.13
    Wells
    0.13
     ventric
    0.12
    Activations Density 0.001%

    No Known Activations