© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79334
    Prev
    Next
    INDEX
    Explanations

    possessive phrases

    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_0_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
     was
    2.42
    s
    1.90
    ه
    1.81
    '
    1.73
    dan
    1.66
    was
    1.66
     that
    1.63
     were
    1.60
    sen
    1.57
    ться
    1.55
    POSITIVE LOGITS
    的结果
    1.27
    的目标
    1.25
    出
    1.24
    ويه
    1.22
    وغ
    1.22
    的生活
    1.20
    да
    1.19
    的光
    1.19
    的能力
    1.16
    وء
    1.16
    Activations Density 0.000%

    No Known Activations