© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66653
    Prev
    Next
    INDEX
    Explanations

    angry

    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
    Not in Any Lists

    No Comments

    Negative Logits
     anger
    0.95
    Fury
    0.91
     fury
    0.89
     Rage
    0.83
     Fury
    0.82
     Anger
    0.82
     rage
    0.80
    怒
    0.76
    愤怒
    0.75
     colère
    0.71
    POSITIVE LOGITS
     고객
    0.40
    ild
    0.40
    لد
    0.38
     গ্রাহ
    0.38
     debtor
    0.37
    貓
    0.37
    |-\
    0.37
    ldata
    0.36
    ಮಾಡ
    0.36
    ộm
    0.36
    Activations Density 0.002%

    No Known Activations