© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4403
    Prev
    Next
    INDEX
    Explanations

    technical documents about measuring things

    oai_token-act-pair · gemini-2.0-flash

    measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     بيها
    -0.76
     مشين
    -0.75
     оригіналу
    -0.68
     Wahrheit
    -0.66
     لينك
    -0.66
     dentelle
    -0.65
    itudinal
    -0.62
    SequentialGroup
    -0.61
    iteracy
    -0.59
    ulipas
    -0.58
    POSITIVE LOGITS
    ThroughAttribute
    0.71
    DebuggerNonUser
    0.63
    __':
    0.62
    Rüyada
    0.55
    Compose
    0.54
    DIFF
    0.54
    libft
    0.54
    dafx
    0.52
     pinulongan
    0.52
    \\\
    0.52
    Activations Density 0.389%

    No Known Activations