© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12953
    Prev
    Next
    INDEX
    Explanations

    historical events or the existence of being.

    oai_token-act-pair · gemini-2.0-flash

    recorded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    jspb
    -0.52
    addWidget
    -0.49
    tgär
    -0.48
    <bos>
    -0.47
    flich
    -0.44
    Bringing
    -0.42
    both
    -0.42
    ERe
    -0.41
     Definitions
    -0.41
    ༻
    -0.41
    POSITIVE LOGITS
    يميديا
    0.77
    niająca
    0.75
     worldwide
    0.75
     world
    0.72
    RTEE
    0.71
     Normdatei
    0.68
    ThroughAttribute
    0.68
     JpaRepository
    0.67
     världen
    0.67
     internazionali
    0.65
    Activations Density 2.559%

    No Known Activations