© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 208333
    Prev
    Next
    INDEX
    Explanations

    multi-year plans and projects

    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_10_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
    é
    0.33
    et
    0.33
     the
    0.32
    á
    0.30
    </h1>
    0.29
    </strong>
    0.29
    лер
    0.29
     of
    0.29
    ية
    0.29
     studded
    0.29
    POSITIVE LOGITS
    ಒ
    0.30
    Have
    0.29
    CONTROL
    0.27
    П
    0.27
    ቒ
    0.27
    Airport
    0.27
    ﺐ
    0.26
    UPDATE
    0.26
    Fonts
    0.26
    CANCEL
    0.26
    Activations Density 0.001%

    No Known Activations