© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14677
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    '][]
    -0.60
    UnusedPrivate
    -0.59
     uitzicht
    -0.54
    findpost
    -0.53
     personal
    -0.52
    atista
    -0.52
    avid
    -0.51
    athie
    -0.50
    MigrationBuilder
    -0.50
    PhysRevD
    -0.50
    POSITIVE LOGITS
     Enlight
    0.50
     Schlaf
    0.47
     uğ
    0.45
     Universitaria
    0.44
    include
    0.44
     gắng
    0.44
     convulsions
    0.44
    ]();
    0.44
     manifestly
    0.43
     Orrell
    0.43
    Activations Density 0.801%

    No Known Activations