© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101258
    Prev
    Next
    INDEX
    Explanations

    signatory change detection

    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_14_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
     decidido
    0.54
     decidiu
    0.52
     recalled
    0.49
    citenamefont
    0.46
    uws
    0.46
    ဠ
    0.46
     pensare
    0.46
    ση
    0.46
     vigente
    0.46
    ᒋ
    0.46
    POSITIVE LOGITS
     كل
    0.46
    A
    0.46
     صي
    0.46
     نهاية
    0.45
     casting
    0.43
    0.41
     spal
    0.41
    capture
    0.41
    Dart
    0.41
    Man
    0.40
    Activations Density 0.000%

    No Known Activations