© 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. 13136
    Prev
    Next
    INDEX
    Explanations

    tokens related to language-specific characters from German, Polish, and French.

    oai_token-act-pair · 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
     createSlice
    -0.90
     صوتيه
    -0.88
    IUrlHelper
    -0.84
     NgModule
    -0.74
     Bioaccumulative
    -0.71
    UserScript
    -0.71
    ngdoc
    -0.71
    Bioaccumulative
    -0.69
     CreateTagHelper
    -0.69
    utilisons
    -0.69
    POSITIVE LOGITS
     OUT
    1.15
     Out
    1.09
     out
    1.06
    Out
    1.03
    out
    0.98
     outs
    0.95
    OUT
    0.94
    outs
    0.92
     Outs
    0.82
    EOUT
    0.77
    Activations Density 0.568%

    No Known Activations