© 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. 238710
    Prev
    Next
    INDEX
    Explanations

    affirmations of personal agency

    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
    하
    0.45
    업
    0.42
    је
    0.40
     کنید
    0.39
    봤
    0.38
    히
    0.38
    들
    0.37
    โซ
    0.37
    را
    0.36
    Ia
    0.36
    POSITIVE LOGITS
     ansiedad
    0.44
    xiety
    0.43
    юще
    0.42
     anxious
    0.41
     scientifiques
    0.41
     ஆண்டு
    0.40
     scientifically
    0.40
     যু
    0.38
     graduellement
    0.38
     manglid
    0.38
    Activations Density 0.000%

    No Known Activations