© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33512
    Prev
    Next
    INDEX
    Explanations

    z, Zn, vec prefixes

    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_31_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
     Coatings
    0.39
     hauling
    0.38
     keeping
    0.38
     replacing
    0.37
    矛盾
    0.37
    \[
    0.37
    年に
    0.36
     Brazil
    0.36
     rowing
    0.36
     gesture
    0.35
    POSITIVE LOGITS
    ষি
    0.39
    츈
    0.38
     สมการ
    0.38
     አይደ
    0.37
    apsingToolbar
    0.37
     কপ
    0.36
    tay
    0.35
     monedas
    0.35
    यंस
    0.35
    glers
    0.34
    Activations Density 0.002%

    No Known Activations