© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208327
    Prev
    Next
    INDEX
    Explanations

    Pacific

    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_56_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
     october
    0.49
     september
    0.44
     november
    0.44
     augustus
    0.43
    菄
    0.41
    sulph
    0.39
     October
    0.39
     december
    0.39
     octubre
    0.39
    琭
    0.38
    POSITIVE LOGITS
     EST
    0.65
    Pacific
    0.63
    EST
    0.61
     UTC
    0.59
    GMT
    0.58
     PST
    0.56
    BST
    0.56
     local
    0.55
     GMT
    0.55
     PDT
    0.54
    Activations Density 0.002%

    No Known Activations