© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11808
    Prev
    Next
    INDEX
    Explanations

    leading whitespace

    oai_token-act-pair · gemini-2.0-flash

    Hexadecimal characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WebVitals
    -0.82
    InSection
    -0.79
     Inscrivez
    -0.63
    AnchorStyles
    -0.62
    CppCodeGen
    -0.62
     ujednoznacz
    -0.59
    ="#"><
    -0.57
    pexpr
    -0.56
    リューション
    -0.56
     către
    -0.55
    POSITIVE LOGITS
     case
    0.76
     Case
    0.66
    case
    0.66
    тьяна
    0.63
    Case
    0.56
     caso
    0.55
    root
    0.53
     ddelweddau
    0.52
     صوتيه
    0.50
     Ho
    0.50
    Activations Density 0.721%

    No Known Activations