© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9105
    Prev
    Next
    INDEX
    Explanations

    phrases about combining or grouping together

    oai_token-act-pair · gemini-2.0-flash

    forming groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Datuak
    -0.78
     estimés
    -0.74
    AutoScaleMode
    -0.73
     وتسجيلات
    -0.68
    Personendaten
    -0.63
    RemoveField
    -0.61
    بوابة
    -0.60
    detectChanges
    -0.59
    RectangleBorder
    -0.58
     Caj
    -0.58
    POSITIVE LOGITS
    <bos>
    0.89
     sharing
    0.51
    !("{
    0.49
     دور
    0.48
    tá
    0.48
     collaboration
    0.45
    ftig
    0.44
    gebra
    0.44
    icorn
    0.44
    Shaders
    0.44
    Activations Density 1.499%

    No Known Activations