© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9756
    Prev
    Next
    INDEX
    Explanations

    the word "hunting" and variations of it, as well as terms related to it, sometimes in the context of Zambia

    oai_token-act-pair · gemini-2.0-flash

    hunting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -2.02
     beginnetje
    -1.04
    __':
    -0.77
    脚注の使い方
    -0.75
    ьаж
    -0.73
    UnusedPrivate
    -0.71
    LookAnd
    -0.69
    sizeCache
    -0.68
    Personensuche
    -0.67
    bewerken
    -0.66
    POSITIVE LOGITS
     other
    0.65
     more
    0.60
     additional
    0.59
     range
    0.59
    mente
    0.59
     use
    0.57
     also
    0.57
     further
    0.56
     stated
    0.55
     respon
    0.54
    Activations Density 0.870%

    No Known Activations