© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12971
    Prev
    Next
    INDEX
    Explanations

    strings of characters commonly found in East Asian names along with the suffix "Jr." or the fragment "christ"

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     "..\..\
    -0.74
     dAtA
    -0.73
    ThemeOverlay
    -0.73
    ConstraintMaker
    -0.73
    ########.
    -0.72
    oa̍t
    -0.72
    tagext
    -0.71
    EndGlobalSection
    -0.71
     ↓,
    -0.70
    RegressionTest
    -0.69
    POSITIVE LOGITS
     ouverts
    0.48
    ,
    0.44
     hand
    0.43
    wachsene
    0.41
    ceira
    0.40
     watch
    0.40
     пов
    0.40
    -
    0.39
     teken
    0.39
     see
    0.39
    Activations Density 0.656%

    No Known Activations