© 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. 9756
    Prev
    Next
    INDEX
    Explanations

    cooking recipes involving temperatures, ingredients and instructions

    oai_token-act-pair · gemini-2.0-flash

    0

    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
     serangga
    -0.62
    WithFormat
    -0.57
    onAttach
    -0.50
    </tbody>
    -0.50
     sachets
    -0.48
     surplus
    -0.48
    Capability
    -0.47
     Gruber
    -0.47
    ม่
    -0.47
    uito
    -0.47
    POSITIVE LOGITS
    ImageContext
    0.75
    MessageTagHelper
    0.68
    Бахар
    0.67
    DeleteBehavior
    0.62
    MigrationBuilder
    0.60
    =$?
    0.59
    KommentareTeilen
    0.58
    Personensuche
    0.57
    featureID
    0.57
     дописавши
    0.55
    Activations Density 0.168%

    No Known Activations