© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13312
    Prev
    Next
    INDEX
    Explanations

    lines including the character '*' often followed by numbers

    oai_token-act-pair · gemini-2.0-flash

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    
    -0.63
     InputDecoration
    -0.59
    Pautan
    -0.57
    InputBorder
    -0.56
     StringTokenizer
    -0.54
    Ārējās
    -0.53
     jLabel
    -0.52
     saites
    -0.51
    بوابة
    -0.51
    makeConstraints
    -0.48
    POSITIVE LOGITS
    //
    0.85
     JADX
    0.67
    /*
    0.66
    ///
    0.62
    Dữ
    0.61
    /******/
    0.60
     endregion
    0.60
     chrétien
    0.60
     escra
    0.60
    __(/*!
    0.60
    Activations Density 1.086%

    No Known Activations