© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9756
    Prev
    Next
    INDEX
    Explanations

    phrases related to network connections and telecommunications, especially in the context of broadcasting or online services.

    oai_token-act-pair · gemini-2.0-flash

    terms related to communication methods

    np_token-act-pair-logits · gpt-4o-mini

    old communication technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    stdc
    -0.68
     network
    -0.62
     Network
    -0.59
     neceff
    -0.59
    tonsoft
    -0.59
     Platform
    -0.58
    Platform
    -0.57
    dası
    -0.57
     platform
    -0.56
     EconPapers
    -0.56
    POSITIVE LOGITS
     fax
    0.57
     land
    0.56
    fax
    0.52
    complexContent
    0.50
     Fax
    0.50
    Fax
    0.49
     Land
    0.47
     SMS
    0.46
     LAND
    0.46
     ferons
    0.46
    Activations Density 2.122%

    No Known Activations