© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7122
    Prev
    Next
    INDEX
    Explanations

    the word "host" in the context of pathogens and parameters

    oai_token-act-pair · gemini-2.0-flash

    hosts and pathogens

    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
     host
    -3.34
     Host
    -3.23
    Host
    -3.09
     hosts
    -3.00
    host
    -2.98
     Hosts
    -2.88
     hosting
    -2.88
     HOST
    -2.78
     Hosting
    -2.64
     hosted
    -2.61
    POSITIVE LOGITS
    WriteLiteral
    0.58
     AttributeSet
    0.52
    DBNull
    0.49
    colgroup
    0.48
    onActivityResult
    0.48
     Lajos
    0.48
    adillas
    0.47
    endwhile
    0.46
    aminen
    0.46
    FieldOffsetTable
    0.45
    Activations Density 2.570%

    No Known Activations