© 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. 200530
    Prev
    Next
    INDEX
    Explanations

    past tense events

    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
    usti
    0.41
    osen
    0.40
    (*
    0.40
     செய்தார்
    0.39
     (*
    0.38
     رج
    0.38
    ے۔
    0.37
    了这个
    0.36
    zz
    0.36
     اولیه
    0.36
    POSITIVE LOGITS
     complied
    0.48
     udziel
    0.41
    ўцаў
    0.41
     обнаружи
    0.41
    苕
    0.40
     granted
    0.40
    हिर
    0.39
    Nobody
    0.38
     découvert
    0.38
     रॉयल
    0.38
    Activations Density 0.001%

    No Known Activations