© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213988
    Prev
    Next
    INDEX
    Explanations

    software, microsft, mulesoft

    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_5_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
    1.84
    ان
    1.47
    an
    1.45
    ні
    1.32
    en
    1.31
    ку
    1.31
    a
    1.30
    est
    1.29
    res
    1.24
    ів
    1.18
    POSITIVE LOGITS
    મ
    1.48
    ಮ
    1.36
    오
    1.24
     plufieurs
    1.22
    Ι
    1.22
    マ
    1.20
    Ак
    1.16
    А
    1.13
    外
    1.11
    프
    1.11
    Activations Density 0.002%

    No Known Activations