© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10284
    Prev
    Next
    INDEX
    Explanations

    words related to journalism and reporting

    oai_token-act-pair · gemini-2.0-flash

    news headlines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ConstraintMaker
    -0.56
     how
    -0.51
    '][]
    -0.45
    ManyToMany
    -0.44
    ...</
    -0.44
    …
    -0.44
     –
    -0.43
     off
    -0.42
    printLine
    -0.42
    awtextra
    -0.41
    POSITIVE LOGITS
    ItemBackground
    0.78
     scolaires
    0.74
    FundMe
    0.69
     féminine
    0.68
     Monfieur
    0.65
     oreilles
    0.65
     للمعارف
    0.64
    lujah
    0.64
    melding
    0.63
     refroid
    0.63
    Activations Density 4.712%

    No Known Activations