© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6185
    Prev
    Next
    INDEX
    Explanations

    words that appear frequently together in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    Mixed data and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    HtmlAttribute
    -0.64
    lebo
    -0.61
    fjspx
    -0.59
    uxxxx
    -0.58
    ProcessEvent
    -0.57
    nodoc
    -0.57
    (!__
    -0.56
    UnsafeEnabled
    -0.55
    InputBorder
    -0.55
     cherchés
    -0.55
    POSITIVE LOGITS
     متعلقه
    0.56
    StackNavigator
    0.45
    getMinutes
    0.45
    getMenuInflater
    0.44
    országban
    0.44
    AspNetCore
    0.43
    φαλ
    0.43
    вець
    0.43
     Balan
    0.43
    esModule
    0.43
    Activations Density 15.169%

    No Known Activations