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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14312
    Prev
    Next
    INDEX
    Explanations

    seemingly unrelated words with shared suffixes or character sequences such as "ers, e, d" and "iano, ld"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    SequentialGroup
    -0.93
    IsContent
    -0.80
    DockStyle
    -0.68
     ModelExpression
    -0.66
     mergeFrom
    -0.64
    >{@
    -0.64
    (!__
    -0.63
    Personendaten
    -0.62
     snippetHide
    -0.61
     propOrder
    -0.61
    POSITIVE LOGITS
    lesi
    0.53
    poel
    0.45
    ViewById
    0.44
     Kessel
    0.43
     Anthem
    0.43
    springframework
    0.43
     cert
    0.41
     Harmonic
    0.41
    Cert
    0.40
    woff
    0.40
    Activations Density 7.314%

    No Known Activations