© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13397
    Prev
    Next
    INDEX
    Explanations

    movie titles, especially those beginning with "The"

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     <<<<<<<<<<<<<<
    -0.67
     sadar
    -0.57
    otheses
    -0.57
    invokeLater
    -0.54
    oredCriteria
    -0.53
     vectorielles
    -0.52
     Awake
    -0.51
    rungsseite
    -0.50
    +#+
    -0.50
    सत
    -0.49
    POSITIVE LOGITS
     chi̍t
    0.69
    Források
    0.61
     resourceCulture
    0.60
     ویکی‌پدیای
    0.58
    WEBPACK
    0.56
     оригіналу
    0.54
    CloseOperation
    0.52
    <()>
    0.50
    EndInit
    0.50
    MENAFN
    0.50
    Activations Density 0.235%

    No Known Activations