© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78503
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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_53_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
     sûr
    0.37
     ব্যব
    0.37
     belief
    0.37
     unbel
    0.36
     Taj
    0.35
     plumage
    0.35
     ऊ
    0.35
    belief
    0.35
     ਫ
    0.35
     Ide
    0.35
    POSITIVE LOGITS
    `)
    0.38
    */)
    0.35
    力を
    0.34
     நடைபெற்ற
    0.34
    ቸ
    0.34
    uva
    0.34
    ತ್ರ
    0.33
    ☰
    0.33
    \|$.
    0.33
    rig
    0.33
    Activations Density 0.002%

    No Known Activations