© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6526
    Prev
    Next
    INDEX
    Explanations

    code with references to "tags", "boxes", or "quizzes"

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    DrawerToggle
    -0.62
    ConstraintMaker
    -0.61
    TagMode
    -0.61
     Chwiliwch
    -0.60
    ImageContext
    -0.60
     Signalez
    -0.60
    featureID
    -0.59
    DockStyle
    -0.57
    ########.
    -0.57
    WriteTagHelper
    -0.56
    POSITIVE LOGITS
    Wide
    0.52
    beforeEach
    0.51
    béco
    0.48
     Wide
    0.48
    casian
    0.48
     braços
    0.46
    uzen
    0.46
    culable
    0.46
    reactivex
    0.46
    shields
    0.45
    Activations Density 3.533%

    No Known Activations