© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43723
    Prev
    Next
    INDEX
    Explanations

    demographic transitions, decline, concerns, crisis, shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     fugitive
    0.37
     m
    0.37
    amo
    0.37
    mortem
    0.36
    hin
    0.36
     finale
    0.35
    Don
    0.35
    edo
    0.35
     do
    0.35
     more
    0.35
    POSITIVE LOGITS
    填写
    0.42
    藁
    0.40
     tattha
    0.38
     ettha
    0.35
    用地
    0.35
    十字
    0.34
    ahuasca
    0.34
    なので
    0.34
     সবকিছু
    0.34
    妸
    0.33
    Activations Density 0.004%

    No Known Activations