© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6844
    Prev
    Next
    INDEX
    Explanations

    funding organizations related to science

    oai_token-act-pair · gemini-2.0-flash

    Coding/Programming

    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
    CreateModel
    -0.60
    interopRequire
    -0.60
    '},
    -0.58
    FailureListener
    -0.58
    原始内容存档
    -0.57
    ècie
    -0.55
     ]}
    -0.52
     arşivlendi
    -0.51
    MLLoader
    -0.51
    eridge
    -0.50
    POSITIVE LOGITS
    Th
    0.57
     Normdatei
    0.56
    th
    0.54
    RenderAtEndOf
    0.51
     Th
    0.50
    webElement
    0.49
    alt
    0.48
    quoise
    0.48
     Administrativna
    0.47
    السكان
    0.47
    Activations Density 0.155%

    No Known Activations