© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    statistics related to American Football and Basketball

    oai_token-act-pair · gemini-2.0-flash

    Technical texts involving numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    rlrl
    -0.60
    IsMutable
    -0.59
    quelize
    -0.59
    tvguidetime
    -0.56
     članak
    -0.54
     couv
    -0.54
     feeders
    -0.53
    ódź
    -0.51
    Hozzáférés
    -0.51
    kPa
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    ArrowToggle
    0.64
    BufferException
    0.61
     يتيمه
    0.58
     COUNT
    0.55
    AnchorTagHelper
    0.53
    ListItemIcon
    0.47
    PointerException
    0.46
     useParams
    0.44
     isInitialized
    0.43
    Activations Density 1.602%

    No Known Activations