© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69397
    Prev
    Next
    INDEX
    Explanations

    personal 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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     firmly
    0.55
     claim
    0.52
     insist
    0.44
     refuse
    0.44
     claims
    0.44
     fails
    0.44
    claim
    0.43
    坚
    0.43
     refuses
    0.42
     contends
    0.42
    POSITIVE LOGITS
    CHAR
    0.39
    GING
    0.38
    cony
    0.38
    BJ
    0.38
    ぶり
    0.37
    GED
    0.36
    changed
    0.35
    UserDefaults
    0.35
     last
    0.35
     разобраться
    0.35
    Activations Density 0.102%

    No Known Activations