© 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. 10683
    Prev
    Next
    INDEX
    Explanations

    the prefix "hal" as part of a longer word

    oai_token-act-pair · gemini-2.0-flash

    hal

    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
     hal
    -2.47
     Hal
    -2.34
    Hal
    -2.30
    hal
    -2.23
    HAL
    -1.72
     HAL
    -1.58
    halo
    -0.97
    halt
    -0.94
    hala
    -0.93
     halide
    -0.90
    POSITIVE LOGITS
     LHC
    0.68
    IonicModule
    0.66
     resourceCulture
    0.65
     defaultstate
    0.63
     فريبيس
    0.60
    Недостатки
    0.59
     للاسماء
    0.59
    AccessorTable
    0.59
    LHC
    0.58
    зулта
    0.58
    Activations Density 0.633%

    No Known Activations