© 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. 176001
    Prev
    Next
    INDEX
    Explanations

    over or excessive

    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
    crib
    0.38
    釘
    0.38
    zü
    0.36
    coons
    0.36
    ENCI
    0.35
    밉
    0.35
     Nab
    0.35
     அடிகள்
    0.35
     Riv
    0.35
    webs
    0.35
    POSITIVE LOGITS
     over
    0.46
    কাত
    0.40
    過
    0.39
     ká
    0.39
    过
    0.38
     üle
    0.38
    過了
    0.38
    確定
    0.37
     quá
    0.36
     über
    0.36
    Activations Density 0.005%

    No Known Activations