© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12569
    Prev
    Next
    INDEX
    Explanations

    prepositions and related words indicating possession or location, along with references to official bodies or code structures.

    oai_token-act-pair · gemini-2.0-flash

    common English words

    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
    Personendaten
    -0.78
    featureID
    -0.77
    PerformLayout
    -0.75
     betweenstory
    -0.69
     ſy
    -0.65
     صوتيه
    -0.65
     nahilalakip
    -0.65
     Comprometido
    -0.65
    <bos>
    -0.65
     Shakspeare
    -0.64
    POSITIVE LOGITS
    handelt
    0.51
    tighet
    0.51
    pekte
    0.50
     MethodInfo
    0.48
    quilo
    0.47
    secutions
    0.47
     torchvision
    0.47
    )−
    0.47
    insics
    0.45
    '--
    0.45
    Activations Density 2.276%

    No Known Activations