© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16137
    Prev
    Next
    INDEX
    Explanations

    math equations and notation

    oai_token-act-pair · gemini-2.0-flash

    dots

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     $\
    -1.70
     \
    -1.32
    $\
    -1.27
    {$\
    -0.96
    ="\
    -0.88
    '\
    -0.85
    ~$\
    -0.85
     $(\
    -0.82
     "\
    -0.81
    {\
    -0.79
    POSITIVE LOGITS
    .
    0.46
    itiés
    0.42
     onData
    0.41
    ™.
    0.40
    rinth
    0.39
    stination
    0.39
    flakes
    0.38
    فاظ
    0.38
    knot
    0.38
    ittäin
    0.38
    Activations Density 11.400%

    No Known Activations