© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197526
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Cogn
    0.42
    há
    0.41
    ॉर
    0.39
    prints
    0.39
    PES
    0.38
    وهات
    0.38
    㞖
    0.37
    Ха
    0.37
    জির
    0.37
    认知
    0.36
    POSITIVE LOGITS
    rome
    0.40
    rometer
    0.39
     draper
    0.38
    灰色
    0.38
     gray
    0.38
     Sah
    0.38
    ോടെ
    0.37
     tille
    0.37
     ND
    0.36
     consensus
    0.36
    Activations Density 0.004%

    No Known Activations