© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8125
    Prev
    Next
    INDEX
    Explanations

    text related to chemical compounds and their effects, especially in the context of agriculture and patents.

    oai_token-act-pair · gemini-2.0-flash

    chemical research

    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
     Wicidata
    -0.67
    featureID
    -0.66
    DeleteBehavior
    -0.65
    WriteTagHelper
    -0.64
    ंदीखरीदारी
    -0.64
     Normdatei
    -0.63
    tonode
    -0.58
     Biôgrafia
    -0.58
     ModelExpression
    -0.57
     Meksiku
    -0.56
    POSITIVE LOGITS
    liance
    0.51
    MENAFN
    0.47
    ய்ய
    0.47
    Stream
    0.46
    orado
    0.46
     contaminants
    0.45
     basins
    0.45
    stream
    0.44
     columnIndex
    0.44
     Stream
    0.43
    Activations Density 9.751%

    No Known Activations