© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36593
    Prev
    Next
    INDEX
    Explanations

    senior citizen

    np_acts-logits-general · gemini-2.5-flash-lite

    citizen/citizens

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    terms referring to elderly individuals.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
     is
    0.79
     as
    0.77
    اری
    0.67
    .
    0.65
    ef
    0.64
    ed
    0.64
    egg
    0.64
    یل
    0.63
    ectomy
    0.63
    ↵
    0.61
    POSITIVE LOGITS
    સભા
    0.68
    ल
    0.56
    的其他
    0.54
    <h2>
    0.54
    ;">
    0.54
    厛
    0.54
     doda
    0.53
     sigue
    0.52
     Coil
    0.52
    ሶች
    0.51
    Activations Density 0.001%

    No Known Activations