© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10667
    Prev
    Next
    INDEX
    Explanations

    clauses starting with "which", and relative pronouns used when providing additional details about a noun.

    oai_token-act-pair · gemini-2.0-flash

    which/who

    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
    AndroidJUnit
    -0.89
    MessageTagHelper
    -0.81
     pinulongan
    -0.79
    AnimationsModule
    -0.77
     كومونز
    -0.75
    انيف
    -0.67
    CppMethod
    -0.64
    хьтан
    -0.63
    IntoConstraints
    -0.61
     réserve
    -0.60
    POSITIVE LOGITS
     fatal
    0.47
    ticles
    0.45
    ❹
    0.45
    PreferredItem
    0.44
     Wikimedijinoj
    0.43
    xions
    0.42
    drawSprites
    0.42
    发表于
    0.42
    opie
    0.42
    оне
    0.42
    Activations Density 0.463%

    No Known Activations