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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11737
    Prev
    Next
    INDEX
    Explanations

    lines of code using the word "value"

    oai_token-act-pair · gemini-2.0-flash

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     value
    -2.34
    value
    -2.23
     Value
    -2.08
    Value
    -1.97
     VALUE
    -1.74
    VALUE
    -1.60
     valeur
    -1.48
     values
    -1.22
     Wert
    -1.21
     valore
    -1.18
    POSITIVE LOGITS
     незавершена
    0.82
    ThroughAttribute
    0.79
    PathVariable
    0.73
    parsedMessage
    0.70
     propOrder
    0.69
    rungsseite
    0.66
    principalColumn
    0.65
    OrBuilder
    0.65
     BoxDecoration
    0.64
    addCriterion
    0.63
    Activations Density 0.361%

    No Known Activations