© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230961
    Prev
    Next
    INDEX
    Explanations

    chateau or schloss and associated place names

    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_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
    ä
    1.32
    t
    1.09
     indépend
    1.08
    ne
    1.07
    ll
    1.03
    nd
    1.02
    d
    1.00
     and
    0.99
    க
    0.95
     allemand
    0.94
    POSITIVE LOGITS
    و
    1.03
    ро
    0.98
    un
    0.98
    িন
    0.97
    гор
    0.93
     as
    0.88
    води
    0.87
    вели
    0.85
    ின்
    0.84
    есть
    0.84
    Activations Density 0.000%

    No Known Activations