© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6153
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to combining components and related concepts

    oai_token-act-pair · gemini-2.0-flash

    terms related to combinations and classifications

    np_token-act-pair-logits · gpt-4o-mini

    combination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     שוליים
    -0.69
    Personendaten
    -0.57
     الحره
    -0.56
     magasiner
    -0.55
     AspNetCore
    -0.54
     tartalomajánló
    -0.54
     تضيفلها
    -0.53
     său
    -0.52
    Datuak
    -0.52
    存于互联网档案馆
    -0.50
    POSITIVE LOGITS
     AppCompatTheme
    0.69
    LayoutStyle
    0.59
     AttributeSet
    0.56
    mtable
    0.56
     Roskov
    0.55
    GraphicsUnit
    0.54
     crossorigin
    0.51
     InputDecoration
    0.50
     Hashimoto
    0.50
     tetanus
    0.50
    Activations Density 13.252%

    No Known Activations