© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61259
    Prev
    Next
    INDEX
    Explanations

    child-like, building, friend

    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_2_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
    的目标
    0.98
    。
    0.93
    の発
    0.86
    的和
    0.86
     it
    0.85
    的研究
    0.84
    `;
    0.84
    の使用
    0.83
    聽
    0.83
    的技术
    0.82
    POSITIVE LOGITS
    at
    1.51
    a
    1.41
    ی
    1.29
    ر
    1.27
    yı
    1.23
    ي
    1.20
    я
    1.18
    ik
    1.13
    dı
    1.13
    ಾ
    1.13
    Activations Density 0.003%

    No Known Activations