© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50550
    Prev
    Next
    INDEX
    Explanations

    second or two

    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_31_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
     ਫ
    0.41
    专门
    0.37
    omn
    0.37
    三十
    0.36
    ⎤
    0.35
    ECON
    0.35
    ֱ
    0.34
    Economy
    0.34
    어서
    0.33
    尃
    0.33
    POSITIVE LOGITS
     two
    0.70
    two
    0.63
     ಎರಡು
    0.61
    两个
    0.60
     ሁለት
    0.59
     TWO
    0.59
     दो
    0.58
    สอง
    0.58
     два
    0.57
     deux
    0.57
    Activations Density 0.081%

    No Known Activations