© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125719
    Prev
    Next
    INDEX
    Explanations

    MetaMask or decomposition

    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_3_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
    ят
    0.58
    skinned
    0.58
    j
    0.56
    ้าน
    0.55
    నూ
    0.55
    ור
    0.55
    ків
    0.54
     Мето
    0.52
    of
    0.51
    de
    0.50
    POSITIVE LOGITS
     for
    0.77
    ৬
    0.67
     to
    0.67
     at
    0.64
     compañía
    0.64
     ję
    0.64
     can
    0.62
    </h3>
    0.62
     where
    0.61
     dü
    0.61
    Activations Density 0.000%

    No Known Activations