© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196717
    Prev
    Next
    INDEX
    Explanations

    programming package names

    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_46_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
    pectral
    0.46
     reim
    0.40
    肪
    0.40
    pect
    0.39
    Tet
    0.38
     mailing
    0.38
     Tet
    0.36
    dincer
    0.34
    配置
    0.34
    ://
    0.34
    POSITIVE LOGITS
     Activity
    0.66
     activity
    0.64
    Activity
    0.62
     attività
    0.61
    activity
    0.59
     actividad
    0.59
    活動
    0.58
     atividade
    0.57
    活动
    0.57
     ACTIVITY
    0.56
    Activations Density 0.000%

    No Known Activations