© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13662
    Prev
    Next
    INDEX
    Explanations

    phrases that are related to governmental or political matters

    oai_token-act-pair · gemini-2.0-flash

    political and social commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Спасылкі
    -0.65
    SqlParameter
    -0.65
    abestanden
    -0.61
     AppModule
    -0.56
    recated
    -0.55
    dataclass
    -0.54
     useCallback
    -0.54
    onets
    -0.53
    phazard
    -0.52
    MethodManager
    -0.52
    POSITIVE LOGITS
     '\\;'
    0.60
     behavi
    0.48
     behavior
    0.45
    httphttps
    0.45
    끄
    0.45
    zarchiwizowane
    0.44
     behavioral
    0.44
    Климат
    0.44
    bigoplus
    0.43
     BEHAVIOR
    0.43
    Activations Density 5.142%

    No Known Activations