© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    Sandbox

    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
    the
    2.14
    ية
    1.80
    𝘁
    1.72
    ுக
    1.71
    Bài
    1.65
    ths
    1.65
    lasting
    1.63
    вить
    1.58
    kan
    1.58
    to
    1.57
    POSITIVE LOGITS
    ဌ
    1.60
     laboratoires
    1.59
     ອ
    1.58
    こと
    1.56
     retrograde
    1.54
    winfx
    1.53
     ferromagnetic
    1.53
    ചെയ്യ
    1.52
     ві
    1.51
     condemn
    1.51
    Activations Density 0.000%

    No Known Activations