© 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. 15100
    Prev
    Next
    INDEX
    Explanations

    words near references to time or date

    oai_token-act-pair · gemini-2.0-flash

    relative time

    np_max-act · gemini-2.0-flash

    next

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    istoitu
    -0.92
     beginnetje
    -0.91
    BeginContext
    -0.83
    AddTagHelper
    -0.83
    Geplaatst
    -0.82
    InputBorder
    -0.78
     Taktlose
    -0.75
     CreateTagHelper
    -0.75
    ClientSize
    -0.74
     HasFactory
    -0.73
    POSITIVE LOGITS
    <bos>
    0.51
    ことで
    0.50
    <eos>
    0.49
     Afterwards
    0.47
    Afterwards
    0.46
     curieux
    0.43
    ilibr
    0.43
    lerde
    0.43
    stående
    0.42
     afterwards
    0.42
    Activations Density 1.689%

    No Known Activations