© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17479
    Prev
    Next
    INDEX
    Explanations

    read instructions

    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_34_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
    alian
    0.45
    찧
    0.41
    imach
    0.39
    ococ
    0.38
    tu
    0.36
    righteous
    0.36
    oun
    0.36
    eller
    0.36
    കര്‍
    0.36
     kayu
    0.35
    POSITIVE LOGITS
     read
    1.60
     reading
    1.54
    อ่าน
    1.51
    读
    1.50
     đọc
    1.47
     읽
    1.46
    阅读
    1.45
     читать
    1.44
     чита
    1.40
     READ
    1.39
    Activations Density 0.123%

    No Known Activations