© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4253
    Prev
    Next
    INDEX
    Explanations

    impact

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    grained
    0.39
     मंड
    0.39
    ্ু
    0.38
     液
    0.38
    segaretro
    0.38
     wind
    0.37
     crane
    0.37
     manh
    0.37
     blowing
    0.36
    Ef
    0.36
    POSITIVE LOGITS
    冲击
    0.61
    沖
    0.57
    impact
    0.56
    Impact
    0.55
    冲
    0.54
     impact
    0.53
     충
    0.52
     Impact
    0.52
     impacted
    0.51
    衝
    0.51
    Activations Density 0.046%

    No Known Activations