© 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. 11288
    Prev
    Next
    INDEX
    Explanations

    a variety of terms related to quantities, locations and attributes.

    oai_token-act-pair · gemini-2.0-flash

    the word "further"

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

    further

    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
     hey
    -0.44
    acher
    -0.42
     Hey
    -0.41
    BeforeMethod
    -0.41
    miyor
    -0.40
     zou
    -0.39
    wikk
    -0.39
    мен
    -0.39
    
    -0.38
     evitando
    -0.38
    POSITIVE LOGITS
     further
    2.09
    further
    2.00
    Further
    1.75
     Further
    1.70
     FURTHER
    1.59
    FURTHER
    1.41
    urther
    1.37
    进一步
    1.27
     farther
    1.11
     verder
    1.09
    Activations Density 3.023%

    No Known Activations