© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214122
    Prev
    Next
    INDEX
    Explanations

    export

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     perdida
    0.45
     chiqar
    0.43
     สาม
    0.41
    ika
    0.40
    oru
    0.40
    Protected
    0.40
    を出
    0.39
    三
    0.39
     काढ
    0.39
    確
    0.39
    POSITIVE LOGITS
     वैरिएंट
    0.40
     ハンド
    0.40
    ハンド
    0.37
    뷊
    0.37
     মর্ম
    0.36
    ение
    0.35
     ܗܘ
    0.35
    terms
    0.35
     TERMS
    0.35
     hwnd
    0.35
    Activations Density 0.000%

    No Known Activations