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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8602
    Prev
    Next
    INDEX
    Explanations

    Diamond Head hike

    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
    𝗻
    3.26
    𝗶
    3.17
    신도시
    2.65
    ة
    2.62
    𝗲
    2.61
    る
    2.61
    इसके
    2.60
    𝘁
    2.55
    聯繫
    2.55
    𝐢
    2.48
    POSITIVE LOGITS
    spaper
    2.56
    н
    2.47
    bung
    2.35
    лябин
    2.27
    ments
    2.26
    lian
    2.22
    lr
    2.22
    lust
    2.18
     المحلي
    2.12
    utional
    2.09
    Activations Density 0.001%

    No Known Activations