© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88744
    Prev
    Next
    INDEX
    Explanations

    VLF frequencies, vs, Volhynia

    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_3_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
    ’
    0.75
    েনে
    0.63
    ید
    0.63
    用の
    0.59
    ادی
    0.59
     Ubuy
    0.58
    äksi
    0.57
    उ
    0.57
    Си
    0.57
    کی
    0.56
    POSITIVE LOGITS
    า
    0.98
    ا
    0.86
    ة
    0.77
    يد
    0.72
    ক
    0.69
    𝐧
    0.68
     reicht
    0.67
    j
    0.65
     a
    0.64
    ק
    0.64
    Activations Density 0.000%

    No Known Activations