© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4215
    Prev
    Next
    INDEX
    Explanations

    repetitive characters used as dividers, often in code or file headers

    oai_token-act-pair · gemini-2.0-flash

    horizontal lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     صوتيه
    -0.57
     bouche
    -0.57
     leçon
    -0.56
    ględ
    -0.56
    endrait
    -0.56
     inoxydable
    -0.56
     odeur
    -0.56
     flèche
    -0.55
     geschafft
    -0.54
     Reſ
    -0.54
    POSITIVE LOGITS
     SafeMath
    0.59
    bootstrapcdn
    0.52
    artifactId
    0.51
    usermodel
    0.49
    httphttps
    0.49
     resourceCulture
    0.48
     nakalista
    0.46
    maxcdn
    0.46
    INCLUDING
    0.46
     MessageBoxIcon
    0.45
    Activations Density 1.826%

    No Known Activations