© 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. 6295
    Prev
    Next
    INDEX
    Explanations

    words associated with politics, elections, or social status.

    oai_token-act-pair · gemini-2.0-flash

    uncommon or specialized terms

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

    Non-English words

    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
     
    -0.45
    其
    -0.44
     v
    -0.44
     was
    -0.44
     so
    -0.44
     native
    -0.44
     S
    -0.43
     each
    -0.43
     su
    -0.42
     do
    -0.42
    POSITIVE LOGITS
    Билгалдахарш
    0.94
     שוליים
    0.94
    RectangleBorder
    0.93
    enumii
    0.92
     kasarigan
    0.92
    GEBURTSDATUM
    0.91
    enumi
    0.91
    rungsseite
    0.85
     Seeder
    0.85
     poffible
    0.84
    Activations Density 6.858%

    No Known Activations