© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49963
    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_55_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
     si
    0.68
    Si
    0.66
     Si
    0.66
    si
    0.61
     manifest
    0.56
    シ
    0.53
     soul
    0.48
     sinal
    0.48
     señal
    0.47
     سی
    0.46
    POSITIVE LOGITS
     Sus
    0.59
     SUS
    0.54
    sus
    0.53
    Sus
    0.51
     tus
    0.48
     Tus
    0.48
     Sush
    0.47
     sus
    0.46
    SUS
    0.43
    暗
    0.41
    Activations Density 0.033%

    No Known Activations