© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14784
    Prev
    Next
    INDEX
    Explanations

    glial cells and processes

    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_40_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
    divider
    0.39
    셔
    0.37
    cvtColor
    0.37
    TintMode
    0.37
     evoked
    0.36
    🛐
    0.35
    াবলীর
    0.35
    lineTo
    0.35
    Divider
    0.35
    胧
    0.35
    POSITIVE LOGITS
     Cout
    0.42
     Patt
    0.41
    无限
    0.40
     jem
    0.39
     республики
    0.39
     GLA
    0.38
     Cougars
    0.38
    ﺰ
    0.38
     za
    0.37
     Gl
    0.37
    Activations Density 0.018%

    No Known Activations