© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33270
    Prev
    Next
    INDEX
    Explanations

    CVE references

    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_40_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
     Br
    0.42
    Up
    0.40
     Up
    0.38
    bran
    0.38
    Bran
    0.38
    越
    0.38
     ఎవ
    0.36
     obesity
    0.36
    obst
    0.36
     Ob
    0.36
    POSITIVE LOGITS
     यो
    0.39
    火山
    0.38
    AsUpIndicator
    0.36
     असुर
    0.35
     sayısı
    0.35
    >−</
    0.35
    ίων
    0.35
     saill
    0.34
     لگا
    0.34
     rel
    0.33
    Activations Density 0.041%

    No Known Activations