© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14702
    Prev
    Next
    INDEX
    Explanations

    words within text about movies or filmography

    oai_token-act-pair · gemini-2.0-flash

    opening parentheses and related symbols

    np_token-act-pair-logits · gpt-4o-mini

    Parentheses and brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     invokingState
    -0.78
    SequentialGroup
    -0.76
    Einzelnachweise
    -0.75
     consultato
    -0.74
    istoitu
    -0.65
    RRect
    -0.63
    PropertyGroup
    -0.60
    SourceChecksum
    -0.57
    BeginInit
    -0.57
    Javadoc
    -0.56
    POSITIVE LOGITS
     (
    0.76
     [
    0.68
     (/
    0.67
     ([
    0.56
     or
    0.56
     (,
    0.52
     /
    0.50
     (;
    0.49
     (),
    0.49
     vagy
    0.48
    Activations Density 2.985%

    No Known Activations