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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10607
    Prev
    Next
    INDEX
    Explanations

    language related to history, potentially pertaining to the middle east

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     AssemblyCulture
    -0.79
     CURIAM
    -0.59
    ReusableCell
    -0.58
    ThroughAttribute
    -0.58
    PerformLayout
    -0.57
    useState
    -0.56
     SwitchCompat
    -0.56
    ⓧ
    -0.54
     useState
    -0.52
    ManagedBean
    -0.52
    POSITIVE LOGITS
    hpp
    0.60
     freedom
    0.54
     FREEDOM
    0.52
    istema
    0.50
    freedom
    0.48
    δώ
    0.47
     Extrem
    0.47
     padre
    0.47
     الحره
    0.46
     Maggiore
    0.46
    Activations Density 2.484%

    No Known Activations