© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168116
    Prev
    Next
    INDEX
    Explanations

    fear

    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_56_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
    -\{
    0.41
     {...
    0.38
    ौज
    0.34
     engel
    0.34
    شارات
    0.33
    utables
    0.33
    …).
    0.33
    竪
    0.33
    ＊＊
    0.32
    Υ
    0.32
    POSITIVE LOGITS
     fears
    3.63
     Fears
    2.81
     feared
    2.59
    恐
    1.70
     fearful
    1.65
     fearing
    1.58
     ভয়
    1.55
     fear
    1.53
    fear
    1.42
     ভয়
    1.41
    Activations Density 0.095%

    No Known Activations