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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4673
    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_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
    ا
    0.45
    er
    0.44
    en
    0.38
    Slice
    0.36
    ʂ
    0.32
    Color
    0.32
    क्व
    0.32
    Infinite
    0.31
    l
    0.31
    끝
    0.31
    POSITIVE LOGITS
     pollutants
    0.45
    ность
    0.42
     carbone
    0.41
    气候
    0.40
     factored
    0.39
     biodegrad
    0.39
     thermodynam
    0.39
     dioxide
    0.38
     ecologically
    0.38
     pollution
    0.38
    Activations Density 0.347%

    No Known Activations