© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5089
    Prev
    Next
    INDEX
    Explanations

    occurrences of "Cl" and density gradients like "sucrose" and "plasma"

    oai_token-act-pair · gemini-2.0-flash

    Cl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     cl
    -2.11
     Cl
    -2.03
    cl
    -1.93
     CL
    -1.92
    Cl
    -1.88
    CL
    -1.87
     clones
    -1.28
     Cli
    -1.27
    Cli
    -1.25
     clon
    -1.23
    POSITIVE LOGITS
    sizeCache
    0.63
    InSection
    0.60
    cshtml
    0.60
     poitrine
    0.56
    μμ
    0.53
    vább
    0.52
     communiquez
    0.52
     universale
    0.52
     Bedding
    0.52
     SEDS
    0.52
    Activations Density 3.315%

    No Known Activations