© 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. 35493
    Prev
    Next
    INDEX
    Explanations

    land

    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
     அமைப்பு
    0.42
    ಕ್ತ
    0.39
    ütter
    0.39
    ᇂ
    0.39
     Ida
    0.39
    韜
    0.38
    ukary
    0.38
    یداری
    0.37
    运
    0.37
     বলিব
    0.37
    POSITIVE LOGITS
    land
    1.45
    LAND
    1.41
    Land
    1.30
     land
    1.27
    lands
    1.27
    landers
    1.23
    陆
    1.18
     Land
    1.16
     LAND
    1.16
    陸
    1.16
    Activations Density 0.000%

    No Known Activations