© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209401
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
     हू
    0.41
     بے
    0.39
    啜
    0.36
    olischen
    0.36
    getAs
    0.34
    甴
    0.34
     hyperplasia
    0.34
     нач
    0.34
     انس
    0.33
     ሆ
    0.33
    POSITIVE LOGITS
     existed
    0.39
    ian
    0.38
    ToIndex
    0.37
     nodded
    0.36
     puta
    0.35
    FTWARE
    0.35
     Mode
    0.35
     Hy
    0.34
    نات
    0.33
     Nod
    0.33
    Activations Density 0.012%

    No Known Activations