© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206355
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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_20_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
     historie
    0.26
     pentru
    0.25
     untuk
    0.25
     washable
    0.24
     Blume
    0.23
    ḥ
    0.23
    haben
    0.23
    hebung
    0.23
    omi
    0.22
    MAE
    0.22
    POSITIVE LOGITS
    apped
    0.24
     TYPES
    0.23
     、
    0.23
     tappa
    0.22
    正如
    0.22
    升级
    0.21
     உற்பத்தி
    0.21
     পল্ল
    0.21
     систем
    0.21
    izers
    0.21
    Activations Density 0.000%

    No Known Activations