© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193662
    Prev
    Next
    INDEX
    Explanations

    not [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    i
    0.92
    מ
    0.89
    u
    0.88
     in
    0.83
    .
    0.81
     professor
    0.74
    It
    0.73
     produ
    0.70
    )
    0.68
     medit
    0.68
    POSITIVE LOGITS
    ка
    1.07
    ки
    0.93
    for
    0.86
    ید
    0.86
    ли
    0.86
     Chúng
    0.79
    ور
    0.79
     Многие
    0.79
     }+\
    0.79
    ал
    0.78
    Activations Density 0.013%

    No Known Activations