© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43185
    Prev
    Next
    INDEX
    Explanations

    prepositions 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_13_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
     again
    0.52
    hipping
    0.49
     side
    0.49
    タ
    0.49
    cie
    0.48
     sympat
    0.48
    ዢ
    0.48
    プチ
    0.48
     adaptation
    0.48
     extensively
    0.47
    POSITIVE LOGITS
     Fehler
    0.53
     لأنه
    0.52
    people
    0.51
     меж
    0.50
    insuku
    0.50
     список
    0.49
    wendungen
    0.49
     ದಾಖ
    0.49
     درجة
    0.48
    fromParams
    0.48
    Activations Density 0.070%

    No Known Activations