© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93696
    Prev
    Next
    INDEX
    Explanations

    throughput

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    Ч
    1.48
     Ч
    1.22
    че
    1.20
     ч
    1.18
    ч
    1.18
     č
    1.16
    을
    1.11
    를
    1.10
    を
    1.06
     Mel
    1.00
    POSITIVE LOGITS
     throughput
    1.40
     Durch
    1.20
    throughput
    1.19
    Durch
    1.02
     спустя
    0.96
     mediante
    0.86
     tramite
    0.86
    可以通过
    0.72
     lewat
    0.72
    通过
    0.71
    Activations Density 0.021%

    No Known Activations