© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5695
    Prev
    Next
    INDEX
    Explanations

    you guys

    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
    م
    1.33
    person
    1.14
    يں
    1.14
    ин
    1.08
    it
    1.03
    way
    1.00
    ्स
    1.00
    ка
    0.99
    ¿
    0.98
    ह
    0.98
    POSITIVE LOGITS
    াদের
    1.22
    𝓽
    1.19
     remed
    1.17
     totalSupply
    1.14
    дів
    1.14
     dn
    1.13
    దయ
    1.10
    tions
    1.10
     bargain
    1.08
    schirm
    1.08
    Activations Density 0.004%

    No Known Activations