© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211398
    Prev
    Next
    INDEX
    Explanations

    phagocytosis and related cells

    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_5_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
    .
    1.33
    n
    1.16
    2
    1.15
    the
    1.05
    ,
    1.04
    al
    1.02
    ра
    1.02
    ;
    1.01
    4
    1.01
    re
    0.98
    POSITIVE LOGITS
    م
    1.94
    ل
    1.83
    ب
    1.69
    л
    1.58
    在
    1.48
    на
    1.46
    ম
    1.44
    ल
    1.42
     in
    1.41
    म
    1.40
    Activations Density 0.000%

    No Known Activations