© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130696
    Prev
    Next
    INDEX
    Explanations

    VBO PBO

    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_6_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
    ),
    1.01
     emphas
    1.00
     ARE
    0.96
    )"
    0.94
    )*
    0.93
    nd
    0.92
    st
    0.91
    )->
    0.91
    t
    0.90
     è
    0.89
    POSITIVE LOGITS
    ان
    1.06
    is
    1.03
     with
    1.02
    يا
    0.99
    出
    0.95
    కు
    0.89
    با
    0.89
    Productos
    0.86
     تاريخ
    0.85
    ەك
    0.85
    Activations Density 0.000%

    No Known Activations