© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 929
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    5
    -0.86
    4
    -0.86
    9
    -0.75
    3
    -0.75
    8
    -0.74
    6
    -0.62
     four
    -0.60
     five
    -0.59
    2
    -0.57
     nineteen
    -0.55
    POSITIVE LOGITS
    matchCondition
    0.69
     sieben
    0.66
     seven
    0.65
     autorytatywna
    0.65
    SharedDtor
    0.59
     jadx
    0.56
    AccessorTable
    0.55
     tujuh
    0.55
     iprot
    0.54
    writeFieldEnd
    0.54
    Activations Density 2.419%

    No Known Activations