© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9055
    Prev
    Next
    INDEX
    Explanations

    example sentence in German related to modal verbs

    oai_token-act-pair · gemini-2.0-flash

    Software or German language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     follow
    -0.62
     be
    -0.58
     generate
    -0.58
     hang
    -0.57
     roll
    -0.57
     derive
    -0.54
     get
    -0.54
     go
    -0.53
     step
    -0.51
     stand
    -0.51
    POSITIVE LOGITS
    RegistryLite
    0.75
    MemoryWarning
    0.73
    ChildScrollView
    0.72
    jsxFileName
    0.69
    WebServlet
    0.69
    RegressionTest
    0.68
    ScopeManager
    0.66
    OGND
    0.66
     noDo
    0.65
    UserScript
    0.65
    Activations Density 0.880%

    No Known Activations