© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    text describing the dangers of using a hunting bow

    oai_token-act-pair · gemini-2.0-flash

    bows and arrows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    JspWriter
    -0.69
     createState
    -0.63
    esModule
    -0.59
     kicked
    -0.54
    Thankyou
    -0.53
    FormTagHelper
    -0.53
     AspNetCore
    -0.52
     propOrder
    -0.52
    XmlAccessorType
    -0.52
     kick
    -0.52
    POSITIVE LOGITS
     draw
    0.56
     spirit
    0.55
     Qui
    0.54
     Sight
    0.52
    sights
    0.52
    draw
    0.50
    ฉ
    0.50
     qui
    0.50
     quiver
    0.50
     sighting
    0.49
    Activations Density 1.820%

    No Known Activations