© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6625
    Prev
    Next
    INDEX
    Explanations

    references to internet culture, especially 4chan

    oai_token-act-pair · gemini-2.0-flash

    Based

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.99
    Geplaatst
    -0.91
     للمعارف
    -0.82
     "..\..\
    -0.81
     typelib
    -0.81
    StoryboardSegue
    -0.78
    ScopeManager
    -0.77
    tagext
    -0.77
    makeConstraints
    -0.76
    setVerticalGroup
    -0.75
    POSITIVE LOGITS
    Based
    0.69
     based
    0.66
     Based
    0.66
    based
    0.63
     cope
    0.60
    BASED
    0.56
     norm
    0.56
     BASED
    0.54
     National
    0.52
     inc
    0.51
    Activations Density 3.363%

    No Known Activations