© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131221
    Prev
    Next
    INDEX
    Explanations

    political figures' names and suffixes

    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_25_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
    lly
    0.52
    ί
    0.45
    ική
    0.45
    í
    0.44
    été
    0.43
    ilion
    0.43
    ön
    0.42
    mia
    0.42
    ô
    0.42
    Expr
    0.42
    POSITIVE LOGITS
     Stupid
    0.43
     Lamborghini
    0.42
     kritik
    0.42
     paintbrush
    0.42
     Quadratic
    0.41
     gzip
    0.41
     stip
    0.39
     unleashing
    0.38
    ებთ
    0.38
     audacious
    0.38
    Activations Density 0.000%

    No Known Activations