© 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. 16051
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables, especially those using symbols like $ and subscripts

    oai_token-act-pair · gemini-2.0-flash

    math symbols

    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
     like
    -1.29
    Like
    -1.07
     LIKE
    -1.06
    .[/
    -1.05
     Like
    -1.05
    like
    -1.02
    .",
    -1.01
    .")
    -1.00
    LIKE
    -1.00
    ."));
    -0.99
    POSITIVE LOGITS
    $-
    0.54
     $-
    0.43
    $-$
    0.32
    -$
    0.32
    ECs
    0.30
    ‐
    0.29
    –
    0.29
    PDA
    0.29
    －
    0.27
     electrónicos
    0.27
    Activations Density 3.237%

    No Known Activations