© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5103
    Prev
    Next
    INDEX
    Explanations

    descriptions of figures holding objects

    oai_token-act-pair · gemini-2.0-flash

    holding

    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
    Negative Logits
    Jîn
    -0.64
    elemField
    -0.63
    ⓘ
    -0.63
    rawDesc
    -0.57
     initView
    -0.56
     مرئيه
    -0.56
    meister
    -0.54
    دانشنامهٔ
    -0.53
    CppMethod
    -0.52
     Orthop
    -0.52
    POSITIVE LOGITS
    TintMode
    0.57
    cipar
    0.53
    setu
    0.50
    Rowan
    0.47
    FieldBuilder
    0.46
    íslu
    0.46
    Fac
    0.44
    یشن
    0.44
    Facing
    0.44
     Bankers
    0.43
    Activations Density 0.716%

    No Known Activations