© 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. 142143
    Prev
    Next
    INDEX
    Explanations

    weather and URLs

    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
     weak
    0.38
    ্ঠ
    0.37
    柳
    0.36
    弱
    0.36
     Weak
    0.35
    ग्नो
    0.34
    কিং
    0.33
     здоро
    0.33
     tala
    0.33
    ⁄
    0.33
    POSITIVE LOGITS
    Grav
    0.41
    ORTYPE
    0.39
    Empire
    0.39
     Override
    0.39
     সিনেমায়
    0.38
    Youtube
    0.38
     empire
    0.38
    ugas
    0.38
     Públic
    0.38
    BBB
    0.38
    Activations Density 0.005%

    No Known Activations