© 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. 9983
    Prev
    Next
    INDEX
    Explanations

    transitions between positive and negative words or ideas

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    ↵↵
    -0.49
     habet
    -0.46
    or
    -0.44
    InputElement
    -0.43
     eorum
    -0.42
    難しい
    -0.42
    ازی
    -0.42
    TypeConverter
    -0.42
     donnée
    -0.42
    most
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.84
     <<<<<<<<<<<<<<
    0.83
    RegressionTest
    0.78
     Italijanski
    0.73
    webElementXpaths
    0.70
    Tikang
    0.70
     }}"></
    0.69
    addCriterion
    0.66
    TagHelper
    0.66
    rrggbb
    0.65
    Activations Density 0.560%

    No Known Activations