© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9875
    Prev
    Next
    INDEX
    Explanations

    a lot of potentially unrelated things that can't be summarized by one sentence

    oai_token-act-pair · gemini-2.0-flash

    news/political discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    OGND
    -0.58
    DispatchToProps
    -0.53
    CodeAttribute
    -0.49
    ächter
    -0.48
     trading
    -0.48
    sidemargin
    -0.47
    erover
    -0.46
    makeText
    -0.46
    thâu
    -0.45
    GroupLayout
    -0.45
    POSITIVE LOGITS
    createCanvas
    0.69
     Monfieur
    0.65
    ❸
    0.64
     '\\;'
    0.62
    therford
    0.60
    ttemberg
    0.59
    Filmographie
    0.59
     doInBackground
    0.59
    Cô
    0.58
     continúas
    0.58
    Activations Density 4.493%

    No Known Activations