© 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. 68457
    Prev
    Next
    INDEX
    Explanations

    your

    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
    些
    0.43
     traveling
    0.38
     Traveling
    0.38
    接
    0.37
     çalışt
    0.37
    hairstyle
    0.36
     bénéficier
    0.35
    inverted
    0.35
    ंकज
    0.35
    慑
    0.35
    POSITIVE LOGITS
     timing
    0.43
    timing
    0.38
    ranu
    0.37
     clashes
    0.37
     जाहिर
    0.36
     času
    0.36
     kett
    0.36
     purchase
    0.35
     merhabalar
    0.35
     times
    0.35
    Activations Density 0.002%

    No Known Activations