© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10622
    Prev
    Next
    INDEX
    Explanations

    capitalized last names, often with preceding initials

    oai_token-act-pair · gemini-2.0-flash

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    irited
    -0.77
     >=",
    -0.73
     Paglinawan
    -0.70
    TemporalType
    -0.64
     <=",
    -0.60
    EMPL
    -0.59
    psack
    -0.59
    msgTypes
    -0.59
    Personendaten
    -0.58
    enging
    -0.57
    POSITIVE LOGITS
    leyebilirsiniz
    0.45
    BagConstraints
    0.45
     gena
    0.44
    aarrggbb
    0.43
     gebouw
    0.43
    пута
    0.43
    DataPropertyName
    0.42
    їна
    0.42
     Nadie
    0.42
    ModelMap
    0.41
    Activations Density 0.386%

    No Known Activations