© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203759
    Prev
    Next
    INDEX
    Explanations

    dead of night

    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
    <h3>
    1.06
     acht
    0.95
     and
    0.91
     dois
    0.88
     ander
    0.88
    จะ
    0.88
    <h4>
    0.87
    <h5>
    0.85
    ના
    0.85
    গত
    0.85
    POSITIVE LOGITS
    t
    1.42
    to
    1.13
    tingham
    1.01
    td
    0.99
    the
    0.95
     ໜອງ
    0.94
    time
    0.90
    tration
    0.88
    st
    0.86
    they
    0.86
    Activations Density 0.007%

    No Known Activations