© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140670
    Prev
    Next
    INDEX
    Explanations

    code and variables

    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_12_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
    t
    0.42
    !
    0.41
    ک
    0.39
    ز
    0.38
    ו
    0.38
    </h2>
    0.38
    ↵↵
    0.38
    아
    0.37
     organi
    0.36
    ል
    0.36
    POSITIVE LOGITS
     نقص
    0.36
     وطالبات
    0.32
     計算
    0.32
     関数
    0.32
    ॉन
    0.32
     Mathf
    0.32
    ᆹ
    0.32
     東京
    0.32
     গিয়েছিল
    0.32
     গিয়েছিল
    0.31
    Activations Density 0.001%

    No Known Activations