© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52526
    Prev
    Next
    INDEX
    Explanations

    single, sole, unique

    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_30_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
    这两个
    0.39
     сначала
    0.38
    两位
    0.37
    ovington
    0.36
    ｖ
    0.36
    ”—
    0.35
    分别为
    0.35
    volta
    0.35
    ьев
    0.35
    }\|_{
    0.35
    POSITIVE LOGITS
     единственный
    0.52
    单一
    0.51
     един
    0.50
     एकमात्र
    0.50
    只有一个
    0.49
     single
    0.47
     jedin
    0.47
     einzige
    0.46
     einzigen
    0.46
     الوح
    0.45
    Activations Density 0.103%

    No Known Activations