© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9702
    Prev
    Next
    INDEX
    Explanations

    fragments of code or data, as well as the word 'and' along with a few other seemingly unrelated words

    oai_token-act-pair · gemini-2.0-flash

    and, $, semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ArrowToggle
    -0.40
    Tikang
    -0.39
     ||
    -0.39
    is
    -0.38
    dall
    -0.38
    all
    -0.37
    deauna
    -0.36
     party
    -0.36
     väl
    -0.36
    tom
    -0.35
    POSITIVE LOGITS
    principalColumn
    0.89
    NameInMap
    0.87
    ########.
    0.77
    setupUi
    0.77
    dafx
    0.75
    Πηγή
    0.72
    +#+#
    0.71
    ParallelGroup
    0.70
     BoxFit
    0.70
     Efq
    0.69
    Activations Density 3.414%

    No Known Activations