© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11028
    Prev
    Next
    INDEX
    Explanations

    sentences that describe options or types of things

    oai_token-act-pair · gemini-2.0-flash

    say "the" or "t"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     HasFactory
    -0.91
    $.
    -0.86
    SequentialGroup
    -0.86
    >\<^
    -0.84
    astéroïdes
    -0.81
     Chwiliwch
    -0.80
    ^(@)
    -0.79
     tartalomajánló
    -0.79
     AttributeSet
    -0.79
    setViewportView
    -0.78
    POSITIVE LOGITS
    en
    0.60
     state
    0.57
     make
    0.55
    n
    0.52
     time
    0.52
    En
    0.51
     n
    0.47
     local
    0.45
     level
    0.45
    l
    0.44
    Activations Density 2.924%

    No Known Activations