© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    terms related to electronics, devices, and computer programming

    oai_token-act-pair · gemini-2.0-flash

    devices with fans/sound/email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    曖昧さ回避
    -0.54
    webElement
    -0.49
     =>
    -0.47
    ++]
    -0.47
    rę
    -0.46
    AutoField
    -0.45
    gave
    -0.45
    mybatisplus
    -0.44
     defaultstate
    -0.44
    arella
    -0.43
    POSITIVE LOGITS
    ſelf
    0.67
     pleaſure
    0.63
     Jefus
    0.63
     Numerade
    0.62
    ſelves
    0.61
     uſe
    0.61
     ſche
    0.60
     Majefty
    0.60
    orsese
    0.59
     diſt
    0.57
    Activations Density 3.403%

    No Known Activations