© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4714
    Prev
    Next
    INDEX
    Explanations

    LL/API client imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    JSONArray
    0.88
    ീ
    0.84
     వచ్చిన
    0.82
    ்து
    0.81
    at
    0.81
     Dere
    0.80
    Deleting
    0.79
    SelectedItem
    0.78
    Declared
    0.78
    Quem
    0.78
    POSITIVE LOGITS
    िंग
    1.06
    ernel
    1.02
    й
    1.00
    ști
    0.98
    an
    0.96
     cí
    0.94
    ছু
    0.94
    ità
    0.94
    aná
    0.89
    ी
    0.88
    Activations Density 0.051%

    No Known Activations