© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10646
    Prev
    Next
    INDEX
    Explanations

    technical writing describing problems, limitations or disadvantages

    oai_token-act-pair · gemini-2.0-flash

    Technical writing/descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     above
    -1.37
    above
    -1.30
     below
    -1.25
    Above
    -1.22
    below
    -1.20
     acima
    -1.14
     Above
    -1.12
    Below
    -1.09
     ABOVE
    -1.07
     Below
    -1.03
    POSITIVE LOGITS
     cas
    0.46
    "
    0.46
     ax
    0.45
     تد
    0.45
     F
    0.43
    },
    0.43
    *
    0.42
    </h5>
    0.42
    ";
    0.41
    %@",
    0.41
    Activations Density 3.277%

    No Known Activations