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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12785
    Prev
    Next
    INDEX
    Explanations

    words related to repetition in a process or experiment, and possibly some math symbols and equations

    oai_token-act-pair · gemini-2.0-flash

    repetition, patterns

    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
    DebuggerNonUser
    -0.90
    __*/
    -0.58
    sidemargin
    -0.57
    erst
    -0.55
    uxxxx
    -0.54
    Diwedd
    -0.53
     NSCoder
    -0.52
     AssemblyVersion
    -0.52
    ReusableCell
    -0.52
     henvisninger
    -0.51
    POSITIVE LOGITS
    riceps
    0.57
    urlencoded
    0.47
    RuleContext
    0.47
    مدیر
    0.46
     elsewhere
    0.43
     balcon
    0.43
    Zacks
    0.43
     プリーツ
    0.43
    őd
    0.42
    曖昧さ回避
    0.42
    Activations Density 0.460%

    No Known Activations