© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149938
    Prev
    Next
    INDEX
    Explanations

    fear or fright

    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_60_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
     scared
    1.81
    恐
    1.80
     scare
    1.75
     fright
    1.73
     scares
    1.66
     frightened
    1.65
     Scare
    1.46
     frighten
    1.39
     terrified
    1.28
    吓
    1.09
    POSITIVE LOGITS
    f
    1.36
     F
    1.29
     пу
    1.05
    пу
    0.98
     الف
    0.85
    F
    0.85
    ف
    0.79
    Pu
    0.75
     pu
    0.74
    pu
    0.74
    Activations Density 0.041%

    No Known Activations