© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3038
    Prev
    Next
    INDEX
    Explanations

    Indian subcontinent cities

    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_5_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
    ва
    3.10
    لان
    2.89
    おり
    2.60
    ल
    2.40
    ب
    2.33
    ட்
    2.31
     उद
    2.27
     tenga
    2.23
    い
    2.19
    cypress
    2.18
    POSITIVE LOGITS
    ్ఞ
    2.57
     constitutive
    2.46
    sé
    2.43
     Polskiej
    2.24
    torn
    2.23
    fichier
    2.22
     réun
    2.21
     rendus
    2.21
    ږي
    2.21
    নাকে
    2.20
    Activations Density 0.022%

    No Known Activations