© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5436
    Prev
    Next
    INDEX
    Explanations

    turkish words

    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
    ل
    1.17
    𝗹
    1.15
    er
    1.10
    oš
    1.08
    नंतर
    1.06
    ために
    1.06
     perkara
    1.05
    a
    1.05
    া
    1.03
    除此之外
    1.03
    POSITIVE LOGITS
     угла
    0.96
     smell
    0.93
    ನ್ನು
    0.90
    𝙀
    0.88
    jsonData
    0.88
    portable
    0.88
    색
    0.87
    тся
    0.87
     transfected
    0.86
    부터
    0.86
    Activations Density 0.002%

    No Known Activations