© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80729
    Prev
    Next
    INDEX
    Explanations

    python code

    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_0_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
    <0x80>
    1.49
    人
    1.45
    的核心
    1.31
    },
    1.27
    0
    1.23
    的处理
    1.23
    és
    1.21
    𝟎
    1.20
    的支持
    1.17
    ０
    1.17
    POSITIVE LOGITS
    ing
    1.84
    ة
    1.66
    ल
    1.58
    л
    1.49
    1.48
    ę
    1.45
    د
    1.44
    이었
    1.42
    ب
    1.37
    ुन
    1.36
    Activations Density 0.004%

    No Known Activations