© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    abstract negativity using words like "garbage" or "tangled", and location relationships using "in", "to", and "between"

    oai_token-act-pair · gemini-2.0-flash

    words related to removal or nullification

    np_token-act-pair-logits · gpt-4o-mini

    in/to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    expandindo
    -0.73
    évaluateur
    -0.66
    latego
    -0.65
    قایناق‌لار
    -0.64
    AddTagHelper
    -0.63
    abestanden
    -0.62
     Мексичка
    -0.61
    makeConstraints
    -0.60
    发表于
    -0.58
     snippetHide
    -0.58
    POSITIVE LOGITS
     nulla
    0.48
    SBATCH
    0.46
    Off
    0.46
    off
    0.45
     Off
    0.44
    cela
    0.43
    freude
    0.42
    phem
    0.42
    zzata
    0.41
    オフ
    0.41
    Activations Density 1.956%

    No Known Activations