© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2673
    Prev
    Next
    INDEX
    Explanations

    mentions of silverware, especially forks, and possibly also swords and other military/eating utensils

    oai_token-act-pair · gemini-2.0-flash

    Parts of objects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     CreateTagHelper
    -0.75
    MigrationBuilder
    -0.75
    soort
    -0.70
     tartalomajánló
    -0.69
     بيها
    -0.68
    GEBURTSDATUM
    -0.67
     autorytatywna
    -0.66
    ']))
    -0.65
    }))
    -0.65
    __*/
    -0.64
    POSITIVE LOGITS
     petals
    0.63
     frame
    0.60
     blade
    0.57
    frame
    0.55
     frames
    0.55
     shell
    0.54
     barrel
    0.54
     leg
    0.54
     stem
    0.53
     lens
    0.52
    Activations Density 2.807%

    No Known Activations