© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13760
    Prev
    Next
    INDEX
    Explanations

    the beginning or end of blocks of code

    oai_token-act-pair · gemini-2.0-flash

    code terms

    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
    mergeFrom
    -0.61
     صوتيه
    -0.59
    FormTagHelper
    -0.59
    UnsafeEnabled
    -0.56
    UIControlState
    -0.54
    CodedInputStream
    -0.53
    HomeAsUpEnabled
    -0.52
    obiology
    -0.51
     steckt
    -0.50
    NOPQRST
    -0.49
    POSITIVE LOGITS
    ruptedException
    0.55
     ono
    0.52
    LookAnd
    0.51
    didSet
    0.49
     LoggerFactory
    0.49
    enderror
    0.47
     mapStateToProps
    0.46
     <=",
    0.46
    campista
    0.46
     PEST
    0.44
    Activations Density 0.607%

    No Known Activations