© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36403
    Prev
    Next
    INDEX
    Explanations

    possessive particle "of"

    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_11_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
    국의
    0.75
    绎
    0.74
    なる
    0.70
    ینک
    0.69
    вающий
    0.65
    치가
    0.64
    ྵ
    0.64
    ಂಬ
    0.63
    لیک
    0.63
    نت
    0.62
    POSITIVE LOGITS
     |
    0.63
     paraphr
    0.60
     –
    0.59
     optionally
    0.59
     stunned
    0.58
     *
    0.57
    –
    0.56
     aliqu
    0.55
    s
    0.55
    ached
    0.53
    Activations Density 0.001%

    No Known Activations