© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 33
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    webElement
    0.43
    ות
    0.43
    ெற்ற
    0.41
     reproach
    0.40
    জানা
    0.39
    ス
    0.39
     extrapolation
    0.38
     chr
    0.36
    యర్
    0.36
     poté
    0.36
    POSITIVE LOGITS
     Với
    0.41
    م
    0.40
     ginh
    0.39
    zuf
    0.39
     custos
    0.39
    ጥረ
    0.39
     cbind
    0.39
    ১
    0.39
    щает
    0.39
     raccol
    0.38
    Activations Density 2.795%

    No Known Activations