© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13094
    Prev
    Next
    INDEX
    Explanations

    text describing 19th and 20th century European political and military events and movements.

    oai_token-act-pair · gemini-2.0-flash

    separation and unification

    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
    -0.56
     initState
    -0.51
     NSCoder
    -0.49
    twimg
    -0.45
     Man
    -0.45
     man
    -0.45
    jsonwebtoken
    -0.44
    |};
    -0.44
     consultato
    -0.43
    JHEP
    -0.43
    POSITIVE LOGITS
     myſelf
    0.69
     Reſ
    0.69
     Monfieur
    0.68
     ſeveral
    0.65
     decoracion
    0.64
     zitate
    0.64
     Efq
    0.63
    UnusedPrivate
    0.63
     auffi
    0.63
     Theſe
    0.62
    Activations Density 1.195%

    No Known Activations