© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3296
    Prev
    Next
    INDEX
    Explanations

    words related to computer software, consoles, and gaming, with some emphasis on issues and settings

    oai_token-act-pair · gemini-2.0-flash

    saving in software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    complexContent
    -0.84
    webElementXpaths
    -0.83
    Personendaten
    -0.82
    GEBURTSDATUM
    -0.82
    HtmlAttribute
    -0.81
    VolleyError
    -0.80
     AssemblyProduct
    -0.79
     ComVisible
    -0.78
    GraphicsUnit
    -0.76
     Euse
    -0.75
    POSITIVE LOGITS
    جموع
    0.53
     stack
    0.44
    aroa
    0.43
     close
    0.41
    ties
    0.40
    chap
    0.40
     C
    0.38
    stack
    0.37
     متعلقه
    0.36
     doen
    0.36
    Activations Density 1.782%

    No Known Activations