© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    code snippets or references to programming concepts

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    featureID
    -0.72
     CreateTagHelper
    -0.65
    reportWebVitals
    -0.63
    Jeografia
    -0.58
     Normdatei
    -0.56
    aarrggbb
    -0.55
    WebVitals
    -0.54
    THISDAY
    -0.53
    setVerticalGroup
    -0.53
     Bourgoin
    -0.52
    POSITIVE LOGITS
     onSave
    0.51
    brać
    0.49
    LikeLike
    0.48
    _'.$
    0.48
    PERATURE
    0.47
    _'+
    0.47
    _
    0.45
    
    0.45
    eſ
    0.45
    =?";
    0.45
    Activations Density 24.390%

    No Known Activations