© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12591
    Prev
    Next
    INDEX
    Explanations

    poorly formatted documents containing citation/reference information

    oai_token-act-pair · gemini-2.0-flash

    Code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    endphp
    -0.66
    quisites
    -0.60
    himovic
    -0.59
     saites
    -0.58
    yntaxException
    -0.54
    .*")]
    -0.54
     impe
    -0.54
    indicato
    -0.53
    ênis
    -0.53
    GOTREF
    -0.52
    POSITIVE LOGITS
     LEYENDO
    0.56
    Kaynakça
    0.51
    xt
    0.46
    GLOBAL
    0.45
     combineReducers
    0.44
    IBAction
    0.43
     mapStateToProps
    0.42
    tagHelperRunner
    0.42
    Cuánto
    0.42
     Niem
    0.41
    Activations Density 5.911%

    No Known Activations