© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12139
    Prev
    Next
    INDEX
    Explanations

    mentions of pollutants and the reduction of pollutants

    oai_token-act-pair · gemini-2.0-flash

    contamination, pollutants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rücks
    -0.52
     néz
    -0.50
    曖昧さ回避
    -0.47
     değ
    -0.47
    ClientSize
    -0.47
    principalTable
    -0.46
    tagext
    -0.44
    onAttach
    -0.44
    ">'+
    -0.44
    ┓
    -0.42
    POSITIVE LOGITS
    itemBuilder
    0.54
    expandindo
    0.53
    KeySpec
    0.52
     rep
    0.52
    acteria
    0.50
    ometri
    0.50
     asf
    0.50
    rations
    0.50
    MessageOf
    0.49
    AnimationsModule
    0.49
    Activations Density 4.084%

    No Known Activations