© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13178
    Prev
    Next
    INDEX
    Explanations

    word fragments ending in 'l' and the word 'able'

    oai_token-act-pair · gemini-2.0-flash

    l/le

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Biôgrafia
    -0.82
    WEBPACK
    -0.81
     مشين
    -0.76
     onCancelled
    -0.75
     surla
    -0.73
     Roskov
    -0.72
    enderror
    -0.71
     NSCoder
    -0.68
     CURLOPT
    -0.66
    Évaluation
    -0.66
    POSITIVE LOGITS
    ABLE
    0.79
    able
    0.79
    <bos>
    0.77
    ABLES
    0.71
    ables
    0.71
     able
    0.68
     Able
    0.66
    bility
    0.64
    ble
    0.63
    ability
    0.61
    Activations Density 0.253%

    No Known Activations