© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36529
    Prev
    Next
    INDEX
    Explanations

    later, as, generally, even

    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
    sman
    0.70
    orak
    0.70
    િવસ
    0.66
    BUGFS
    0.66
    kprop
    0.66
    ⴼ
    0.66
    tan
    0.65
     of
    0.64
    moc
    0.63
    keszt
    0.62
    POSITIVE LOGITS
    ร
    0.82
    ι
    0.74
    ט
    0.73
    д
    0.73
    -
    0.70
    u
    0.69
    с
    0.66
    з
    0.66
    )-\
    0.64
    อ
    0.63
    Activations Density 0.105%

    No Known Activations