© 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. 8705
    Prev
    Next
    INDEX
    Explanations

    numbers with periods and forward slashes, as well as min, js, and button words that often appear in code

    oai_token-act-pair · gemini-2.0-flash

    numbers 3 and 7

    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
     d
    -0.48
    я
    -0.44
     pra
    -0.44
     kre
    -0.43
     Cri
    -0.42
     Da
    -0.41
     Ca
    -0.41
    atorium
    -0.41
     Grand
    -0.41
     ca
    -0.40
    POSITIVE LOGITS
    XmlAccessorType
    1.08
     للاسماء
    1.02
    principalColumn
    0.98
    Personendaten
    0.98
     pinulongan
    0.98
    OGND
    0.94
    archiviato
    0.94
    ьаж
    0.94
     дописавши
    0.92
    GEBURTSDATUM
    0.92
    Activations Density 0.481%

    No Known Activations