© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32631
    Prev
    Next
    INDEX
    Explanations

    different types or kinds

    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_7_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
    .
    0.64
    -
    0.61
    _
    0.48
    ↵
    0.43
    \
    0.39
    EN
    0.36
    !
    0.36
    {
    0.35
    .-
    0.34
    ES
    0.33
    POSITIVE LOGITS
    is
    0.40
     for
    0.40
    for
    0.39
    at
    0.38
    ecek
    0.32
     мама
    0.32
    has
    0.31
    सामान्यीकृत
    0.31
     verschied
    0.31
     ලද
    0.31
    Activations Density 0.004%

    No Known Activations