© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10612
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people and places

    oai_token-act-pair · gemini-2.0-flash

    family history

    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
    to
    -0.45
    etc
    -0.42
    for
    -0.40
    რ
    -0.38
    po
    -0.38
    such
    -0.35
    ñ
    -0.35
    To
    -0.34
    anges
    -0.33
    mentioned
    -0.33
    POSITIVE LOGITS
     tartalomajánló
    0.85
    EDEFAULT
    0.81
    RegressionTest
    0.81
    BeginContext
    0.76
    MemoryWarning
    0.76
    RenderAtEndOf
    0.75
     Monfieur
    0.74
     dAtA
    0.73
     resourceCulture
    0.72
     whoſe
    0.71
    Activations Density 5.870%

    No Known Activations