© 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. 5730
    Prev
    Next
    INDEX
    Explanations

    to consider or to think

    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
    𝙘
    2.43
    potent
    2.25
    𝙜
    2.21
    𝙨
    2.10
    𝙖
    2.06
     Appliances
    2.04
    تي
    2.03
    𝒖
    1.99
     siehe
    1.97
    عات
    1.97
    POSITIVE LOGITS
    mêmes
    2.40
     значительно
    2.32
     pousse
    2.21
     Questa
    2.16
    ță
    2.11
     juda
    2.09
    nées
    2.08
    मस्कार
    2.08
     opération
    2.08
    ioane
    2.06
    Activations Density 0.054%

    No Known Activations