© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2126
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns + common nouns

    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_39_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
     familiari
    0.39
     প্রতিষ্ঠানের
    0.38
    দান
    0.38
    机的
    0.38
     ቤ
    0.38
    onomic
    0.37
     machines
    0.37
    orks
    0.37
     antenna
    0.37
    ","/
    0.37
    POSITIVE LOGITS
     tinnitus
    0.42
     Pest
    0.40
     Zu
    0.39
     akadem
    0.39
    금융
    0.37
     Akadem
    0.37
     suppuration
    0.37
    слов
    0.36
     gastritis
    0.36
     pest
    0.35
    Activations Density 0.153%

    No Known Activations