© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154933
    Prev
    Next
    INDEX
    Explanations

    beginnings and endings

    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_50_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
    LOY
    0.42
     RAB
    0.40
    끌
    0.37
    Op
    0.37
     esbo
    0.37
    proliferation
    0.37
    apl
    0.37
     پروف
    0.37
    போ
    0.36
    liferation
    0.36
    POSITIVE LOGITS
    ји
    0.43
     diamonds
    0.39
     Matsumoto
    0.38
    ई
    0.38
    ｊ
    0.38
     Chowdhury
    0.38
     Kisi
    0.38
     jí
    0.37
     cittadini
    0.37
    熵
    0.37
    Activations Density 0.000%

    No Known Activations