© 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. 159163
    Prev
    Next
    INDEX
    Explanations

    ants

    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
    业协会
    0.41
    Ella
    0.38
     Junius
    0.38
     Donne
    0.38
     Johanna
    0.37
     Ella
    0.37
    Elliott
    0.37
    ⑵
    0.36
     حسين
    0.36
    ጁ
    0.36
    POSITIVE LOGITS
    antz
    0.49
    манов
    0.42
     antr
    0.41
     ανθ
    0.41
    દર્
    0.40
     Antim
    0.40
    عد
    0.39
    ferrer
    0.39
     Sov
    0.37
     Ants
    0.37
    Activations Density 0.008%

    No Known Activations