© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106387
    Prev
    Next
    INDEX
    Explanations

    decision making

    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_1_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
    ی
    1.15
     on
    1.14
    ння
    1.07
    ]
    1.07
    и
    1.02
    은
    0.99
    ının
    0.98
    чення
    0.94
    AZIONE
    0.91
     an
    0.90
    POSITIVE LOGITS
    ar
    1.71
    ق
    1.47
    as
    1.46
    ون
    1.46
    ur
    1.41
    ant
    1.38
    el
    1.31
    ol
    1.31
    ن
    1.30
    et
    1.27
    Activations Density 0.001%

    No Known Activations