© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106300
    Prev
    Next
    INDEX
    Explanations

    "er" followed by punctuation or "of"

    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_1_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
    ig
    1.49
    ة
    1.45
    us
    1.42
    og
    1.41
    。
    1.33
    ية
    1.27
    ీ
    1.24
    ü
    1.21
    í
    1.19
    č
    1.16
    POSITIVE LOGITS
    ل
    0.93
    䡃
    0.93
     माध्यम
    0.91
     Yer
    0.90
     familiari
    0.89
    事に
    0.88
    ष्मान
    0.88
    两
    0.88
    InterfaceLine
    0.87
    p
    0.87
    Activations Density 0.000%

    No Known Activations