© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14599
    Prev
    Next
    INDEX
    Explanations

    sentences expressing conditional or causal relationships

    oai_token-act-pair · gemini-2.0-flash

    technical instructions/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     nakalista
    -0.74
    يميديا
    -0.57
     sino
    -0.57
     resourceCulture
    -0.55
    AlterField
    -0.55
     lenker
    -0.54
     متعلقه
    -0.53
    ômico
    -0.51
    tvguidetime
    -0.50
    dil
    -0.50
    POSITIVE LOGITS
    taan
    0.64
    brigens
    0.64
    Shutterstock
    0.63
    rshire
    0.56
     AssemblyVersion
    0.55
    ridgeshire
    0.53
    ByteString
    0.51
     onwards
    0.51
    SupportActionBar
    0.50
    photobucket
    0.50
    Activations Density 2.643%

    No Known Activations