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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14941
    Prev
    Next
    INDEX
    Explanations

    the word "safe" when describing states in a political context

    oai_token-act-pair · gemini-2.0-flash

    safe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     MainAxisSize
    -0.76
    setVerticalGroup
    -0.53
    WriteLiteral
    -0.50
    phazard
    -0.50
    ']?>
    -0.49
    Parcelize
    -0.49
     BrowserModule
    -0.49
     sağ
    -0.48
     intérêts
    -0.48
    NamedQueries
    -0.47
    POSITIVE LOGITS
     Roskov
    0.59
    onucle
    0.54
    öll
    0.51
    fitriones
    0.50
    spn
    0.50
    Dise
    0.49
    umps
    0.49
    ubel
    0.49
    MergeFrom
    0.49
    leby
    0.49
    Activations Density 0.619%

    No Known Activations