© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4427
    Prev
    Next
    INDEX
    Explanations

    code snippets including diff information with timestamps

    oai_token-act-pair · gemini-2.0-flash

    Code/Log Files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     >=",
    -0.93
    SpringBootTest
    -0.90
    ंदीखरीदारी
    -0.78
    sidemargin
    -0.75
    Personendaten
    -0.75
    SBATCH
    -0.74
    matchCondition
    -0.73
    RenderAtEndOf
    -0.72
    setVerticalGroup
    -0.72
     CreateTagHelper
    -0.69
    POSITIVE LOGITS
    0
    0.49
     Tema
    0.43
    out
    0.43
     gag
    0.42
    cline
    0.41
     Sardin
    0.41
     chains
    0.40
    0.40
    Tema
    0.40
    ajs
    0.40
    Activations Density 1.705%
    No Known Activations