© 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. 5688
    Prev
    Next
    INDEX
    Explanations

    the prefix "pal"

    oai_token-act-pair · gemini-2.0-flash

    pal

    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
    afficheront
    -0.73
     EClass
    -0.71
    født
    -0.68
     createState
    -0.67
    SBATCH
    -0.67
    Obrázky
    -0.64
    SequentialGroup
    -0.63
     NSError
    -0.62
    ScopeManager
    -0.62
    참고
    -0.62
    POSITIVE LOGITS
     Mit
    0.45
     mit
    0.44
     am
    0.44
    adine
    0.42
     Bo
    0.41
    iség
    0.40
    am
    0.40
     سما
    0.40
    atial
    0.40
    andri
    0.40
    Activations Density 0.375%

    No Known Activations