© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133774
    Prev
    Next
    INDEX
    Explanations

    decolonization, relocation

    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_1_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
     Championship
    1.09
    い
    0.99
    า
    0.93
    ia
    0.93
     (
    0.82
     Mediterranean
    0.81
     Drupal
    0.80
     Section
    0.80
    д
    0.80
     SUV
    0.80
    POSITIVE LOGITS
    t
    1.59
     for
    1.45
    2
    1.45
    to
    1.34
    7
    1.32
    m
    1.28
    4
    1.22
    for
    1.20
    5
    1.20
    1
    1.20
    Activations Density 0.000%

    No Known Activations