© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3381
    Prev
    Next
    INDEX
    Explanations

    break down the

    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
    ionalità
    0.61
     говорить
    0.58
    ture
    0.58
    ⋮
    0.56
    horizontalLayout
    0.55
     permeates
    0.53
    بالإنجليزية
    0.53
     disponibilité
    0.53
    ่อน
    0.53
    द्रोह
    0.53
    POSITIVE LOGITS
    рок
    0.47
    ια
    0.45
    कालीन
    0.41
    ї
    0.40
    𝗶
    0.40
    口
    0.40
    ுகிறார்கள்
    0.38
    अ
    0.38
    और
    0.38
    वादियों
    0.38
    Activations Density 0.100%

    No Known Activations