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-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6923
    Prev
    Next
    INDEX
    Explanations

    text potentially describing plant species

    oai_token-act-pair · gemini-2.0-flash

    plant related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SharedCtor
    -0.53
     cadrul
    -0.48
     rara
    -0.47
    enumi
    -0.47
     mobile
    -0.46
     plastica
    -0.46
    müş
    -0.44
     móvil
    -0.44
     ügy
    -0.44
    instancetype
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.74
    AndEndTag
    0.63
     grasses
    0.62
     plant
    0.60
    ysław
    0.60
     plants
    0.60
    ❋
    0.60
    plant
    0.58
     Plant
    0.57
     Plants
    0.57
    Activations Density 0.609%

    No Known Activations