© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203692
    Prev
    Next
    INDEX
    Explanations

    xl size specifiers

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

    sizes

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

    tokens related to large model sizes, such as those ending in "XL" or "XXL".

    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_6_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
    ᱗
    1.17
     اين
    1.11
    <0x0D>
    1.04
    問い合わせ
    1.02
    });
    1.01
     abrió
    1.00
    ări
    1.00
    0.99
    ０
    0.98
    <0xF3>
    0.97
    POSITIVE LOGITS
    h
    1.93
    t
    1.90
    k
    1.58
    s
    1.46
    f
    1.46
    ä
    1.40
    d
    1.38
    v
    1.37
    e
    1.34
    l
    1.34
    Activations Density 0.000%

    No Known Activations