© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88029
    Prev
    Next
    INDEX
    Explanations

    alpine AS builder

    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_23_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
    两
    0.50
     قائم
    0.49
     جديدة
    0.48
     പുതിയ
    0.48
    娴
    0.48
    潍
    0.47
     புதிய
    0.46
    تص
    0.45
     مقار
    0.45
    文中
    0.43
    POSITIVE LOGITS
    odium
    0.46
     consequatur
    0.45
    "
    0.43
     amore
    0.42
    カ
    0.41
    <0x8E>
    0.41
    ισε
    0.41
     artefact
    0.41
     의한
    0.40
    oderma
    0.40
    Activations Density 0.000%

    No Known Activations