© 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. 6456
    Prev
    Next
    INDEX
    Explanations

    words starting with "fl" or containing "us"

    oai_token-act-pair · gemini-2.0-flash

    fl

    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
     <>",
    -0.63
    parsedMessage
    -0.59
     Réponses
    -0.56
     esternos
    -0.55
     ostavi
    -0.54
    SourceChecksum
    -0.49
    bạn
    -0.48
    aarrggbb
    -0.48
    HasMaxLength
    -0.47
    RegressionTest
    -0.47
    POSITIVE LOGITS
    xer
    0.58
     onData
    0.58
    rxjs
    0.56
    ysql
    0.55
    xtext
    0.54
    oneofs
    0.54
     StatelessWidget
    0.54
    textTheme
    0.53
     CURLOPT
    0.52
    BuildContext
    0.52
    Activations Density 9.713%

    No Known Activations