© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13875
    Prev
    Next
    INDEX
    Explanations

    nouns turned into actions by suffixes such as -tion, -ment, -ance, and -ence

    oai_token-act-pair · gemini-2.0-flash

    formal topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    CPtr
    -0.63
    서
    -0.48
     ISNI
    -0.48
    zean
    -0.46
    ">//
    -0.44
    TProtocol
    -0.44
    star
    -0.43
    vd
    -0.43
    usercontent
    -0.42
     incluem
    -0.42
    POSITIVE LOGITS
    TargetException
    0.68
     asmen
    0.65
    ülle
    0.56
     vPvB
    0.56
     Sleeve
    0.56
     sauvage
    0.56
     TextFormField
    0.56
    SuppressMessage
    0.55
    ỡng
    0.54
    Manbalar
    0.54
    Activations Density 1.631%

    No Known Activations