© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5705
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to promoting things on the internet, especially with links

    oai_token-act-pair · gemini-2.0-flash

    websites and online presence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    󠁣
    -0.67
    ParallelGroup
    -0.61
    dium
    -0.53
    umatic
    -0.52
    TargetApi
    -0.52
    цездатний
    -0.52
    GestureDetector
    -0.50
    thickness
    -0.48
     untere
    -0.47
    ÚBL
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.72
    }))
    0.63
     ujednoznacz
    0.55
    makeConstraints
    0.52
    parsedMessage
    0.51
     &___
    0.49
    rawDesc
    0.48
    oredCriteria
    0.47
     المعيارى
    0.47
    srcs
    0.46
    Activations Density 3.810%

    No Known Activations