© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13922
    Prev
    Next
    INDEX
    Explanations

    vocabulary terms and descriptions from chemistry, biology and physics

    oai_token-act-pair · gemini-2.0-flash

    natural phenomena

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bootstrapcdn
    -0.73
    DataAnnotations
    -0.72
     transfieras
    -0.64
    RenderAtEndOf
    -0.62
    ScopeManager
    -0.58
     magasiner
    -0.55
    EndGlobalSection
    -0.54
    ContextHolder
    -0.54
    ❋
    -0.54
    ContentAsync
    -0.53
    POSITIVE LOGITS
     renon
    0.59
     optimised
    0.58
     getir
    0.57
     calloc
    0.55
     {}),
    0.54
    })();
    0.54
     optimisation
    0.53
    relaxed
    0.53
     Personalised
    0.53
    orienta
    0.53
    Activations Density 2.679%

    No Known Activations