Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 8995
    Prev
    Next
    INDEX
    Explanations

    get started

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     away
    0.93
    away
    0.82
     Away
    0.73
     AWAY
    0.72
    糖尿
    0.70
    strongly
    0.66
    ടാ
    0.65
    僵
    0.65
     strongly
    0.64
    збе
    0.64
    POSITIVE LOGITS
     haz
    0.74
     gehören
    0.72
    出し
    0.71
     pinn
    0.71
     Desa
    0.70
     hjæl
    0.69
     Dest
    0.68
    抬头
    0.67
     العين
    0.67
     podej
    0.67
    Activations Density 0.001%

    No Known Activations