© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12724
    Prev
    Next
    INDEX
    Explanations

    technical specifications and sales arguments for hardware/software

    oai_token-act-pair · gemini-2.0-flash

    product sales process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    帖最后由
    -0.59
    Insee
    -0.54
    Personendaten
    -0.50
    原始内容存档于
    -0.49
    ंदीखरीदारी
    -0.49
    atillas
    -0.48
    ciclop
    -0.48
    แน
    -0.48
    Erreferentziak
    -0.48
    Diwedd
    -0.47
    POSITIVE LOGITS
     Pelo
    0.59
    MessageTagHelper
    0.59
    gere
    0.59
    fara
    0.58
     Pallas
    0.57
    kuuta
    0.56
     cuillère
    0.56
     TÉCN
    0.54
    keras
    0.54
     aktive
    0.54
    Activations Density 0.350%

    No Known Activations