© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8497
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and theorems

    oai_token-act-pair · gemini-2.0-flash

    math notation

    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
    <b>
    -0.83
    <em>
    -0.75
    <strong>
    -0.74
    <u>
    -0.74
    <i>
    -0.72
     démocr
    -0.67
    ">"
    -0.66
     avulla
    -0.66
    <sub>
    -0.64
    (_
    -0.63
    POSITIVE LOGITS
     BEND
    0.52
     $\%
    0.50
    횟
    0.46
    arote
    0.45
     zir
    0.43
     \%)
    0.43
    __":
    
    0.42
     rai
    0.42
    slant
    0.41
     ApiException
    0.41
    Activations Density 29.748%

    No Known Activations