© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31106
    Prev
    Next
    INDEX
    Explanations

    different types and situations

    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_31_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
    様
    0.29
    륨
    0.28
     steam
    0.27
    DRA
    0.27
     revived
    0.27
     Ipsum
    0.26
    össä
    0.26
    백
    0.26
    rama
    0.26
     plume
    0.25
    POSITIVE LOGITS
     manejo
    0.31
     négoci
    0.30
     pembelian
    0.29
    ৃহে
    0.29
    病情
    0.28
    үй
    0.28
    oinette
    0.28
    ग्गा
    0.27
    राबाद
    0.27
     کلی
    0.27
    Activations Density 0.000%

    No Known Activations