© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3961
    Prev
    Next
    INDEX
    Explanations

    words related to customer service, appliances, and/or tech industry jobs

    oai_token-act-pair · gemini-2.0-flash

    start of new context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    脚注の使い方
    -0.65
    gypti
    -0.59
     kasarigan
    -0.59
     &___
    -0.57
    <?
    -0.55
     awakeFromNib
    -0.54
    期刊论文
    -0.53
    typeorm
    -0.53
    Parcelize
    -0.52
    ModelBuilder
    -0.50
    POSITIVE LOGITS
    __(/*!
    0.58
    ilight
    0.54
     platí
    0.53
    isiaj
    0.52
    wikkel
    0.52
    Personensuche
    0.51
    abestanden
    0.49
    jalá
    0.49
    mtd
    0.49
     Wendell
    0.48
    Activations Density 14.308%

    No Known Activations