Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 938
    Prev
    Next
    INDEX
    Explanations

    words related to crafting and fabric, with a secondary detection of low costs and alternatives.

    oai_token-act-pair · gemini-2.0-flash

    cheap cost inexpensive affordable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    awtextra
    -0.60
    AccessorTable
    -0.58
    ChildScrollView
    -0.57
    labelledby
    -0.56
    __*/
    -0.55
    HttpEntity
    -0.52
     endforeach
    -0.52
    posedge
    -0.51
    ミナル
    -0.49
    AddColumn
    -0.48
    POSITIVE LOGITS
    irical
    0.71
    enumii
    0.63
     Wikimedijinoj
    0.62
    ⓧ
    0.56
    Rhestr
    0.54
     Horde
    0.53
     cheaply
    0.52
     المعيارى
    0.52
    actéristique
    0.52
     hastily
    0.51
    Activations Density 1.833%

    No Known Activations