© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12412
    Prev
    Next
    INDEX
    Explanations

    math-related text with a focus on symbolic variables, equations, and problem-solving.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ddelweddau
    -0.60
     ProtoMessage
    -0.59
    contentLoaded
    -0.58
    ProcessEvent
    -0.54
     <=",
    -0.53
    참고
    -0.50
    ValueStyle
    -0.50
     rhestr
    -0.49
    曖昧さ回避
    -0.49
     Olms
    -0.48
    POSITIVE LOGITS
    ulario
    0.52
     InputDecoration
    0.52
    PhysRev
    0.46
    shadowRadius
    0.45
    inetic
    0.44
    aryen
    0.44
     createSlice
    0.43
    braith
    0.41
    ̍
    0.40
    anasia
    0.40
    Activations Density 0.618%

    No Known Activations