© 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. 77902
    Prev
    Next
    INDEX
    Explanations

    Greek words

    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
     mol
    0.70
     Mol
    0.64
    Mol
    0.62
    mol
    0.57
     molt
    0.48
     MOL
    0.45
     mols
    0.44
    𝒄
    0.44
     Dere
    0.43
    ｃ
    0.42
    POSITIVE LOGITS
     Beb
    0.41
    ার্টমেন্ট
    0.40
     سا
    0.39
     SAP
    0.39
     zákaz
    0.39
     Bă
    0.38
    SAP
    0.38
     Tyrone
    0.38
     змо
    0.37
     GQ
    0.37
    Activations Density 0.001%

    No Known Activations