© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 206646
    Prev
    Next
    INDEX
    Explanations

    anger and negative emotions

    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
    ı
    0.44
     الطرف
    0.42
    uk
    0.40
     uk
    0.40
     மேற்க
    0.39
    @
    0.39
     colesterol
    0.39
     श्रद्धाल
    0.38
    æng
    0.38
    árm
    0.38
    POSITIVE LOGITS
     justice
    0.43
    Justice
    0.39
     transgression
    0.39
     eradic
    0.38
     soir
    0.38
    tLogRow
    0.38
    鋤
    0.38
     miser
    0.38
     Justice
    0.37
     excise
    0.37
    Activations Density 0.005%

    No Known Activations