© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13058
    Prev
    Next
    INDEX
    Explanations

    television news programs

    oai_token-act-pair · gemini-2.0-flash

    news broadcasts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    COUVER
    -0.59
    ButtonStyle
    -0.57
     Приступљено
    -0.52
    ⓧ
    -0.52
     nakalista
    -0.49
     skak
    -0.48
    SequentialGroup
    -0.48
     band
    -0.47
    protobuf
    -0.47
    didSet
    -0.47
    POSITIVE LOGITS
    setRotation
    0.49
    ANSA
    0.49
     Rota
    0.48
    IndentedString
    0.48
     estekak
    0.48
    Caval
    0.47
     Bakersfield
    0.47
    licka
    0.47
    OnInit
    0.47
     azar
    0.46
    Activations Density 2.622%

    No Known Activations