© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    incomplete code snippets mixed with other text, especially code with underscores

    oai_token-act-pair · gemini-2.0-flash

    pass

    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
    StructEnd
    -0.67
    ValueStyle
    -0.67
     disambiguazione
    -0.65
     himo
    -0.59
     ""],
    -0.56
     calendriers
    -0.56
     متعلقه
    -0.56
     الحره
    -0.55
    WithIOException
    -0.54
    évaluateur
    -0.53
    POSITIVE LOGITS
     kehadiran
    0.56
    다고
    0.52
    舶
    0.51
    pherd
    0.50
    Metodo
    0.49
    YSTEM
    0.49
    dataclass
    0.48
    culated
    0.47
    sspiel
    0.47
     malheureux
    0.47
    Activations Density 3.545%

    No Known Activations