© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2984
    Prev
    Next
    INDEX
    Explanations

    phrases that include "another" that may be used to compare things

    oai_token-act-pair · gemini-2.0-flash

    Comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     kasarigan
    -0.85
     estekak
    -0.69
    SBATCH
    -0.65
    __':
    -0.54
    Билгалдахарш
    -0.53
    andReturn
    -0.48
     traves
    -0.47
    Bảo
    -0.47
     devrez
    -0.46
     decre
    -0.46
    POSITIVE LOGITS
    triangleq
    0.53
     NKC
    0.50
    енча
    0.48
     chi̍t
    0.47
    ać
    0.47
    }}],
    0.47
    USAL
    0.46
     ولی
    0.46
    TintMode
    0.46
    osuke
    0.46
    Activations Density 1.008%

    No Known Activations