© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12295
    Prev
    Next
    INDEX
    Explanations

    words or characters often found in academic or technical publications

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    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
    poel
    -0.62
    }');
    -0.60
    ')));
    -0.60
    Những
    -0.60
    intahan
    -0.59
    ApiModelProperty
    -0.58
    Personendaten
    -0.57
    higer
    -0.56
     Moraes
    -0.55
    [])
    -0.54
    POSITIVE LOGITS
    OGND
    0.61
    ContentAsync
    0.52
     viewDidLoad
    0.52
    tagHelperRunner
    0.51
    RetentionPolicy
    0.50
     ſever
    0.50
    ="#"><
    0.49
    tead
    0.48
    PyExc
    0.47
    Vist
    0.47
    Activations Density 3.726%

    No Known Activations