© 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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13858
    Prev
    Next
    INDEX
    Explanations

    words related to updating, changing, and influencing

    oai_token-act-pair · gemini-2.0-flash

    forms of "to be"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     is
    -0.91
     does
    -0.77
     has
    -0.77
     knows
    -0.72
     goes
    -0.71
     gets
    -0.69
     takes
    -0.66
     realizes
    -0.66
     becomes
    -0.66
     begins
    -0.65
    POSITIVE LOGITS
     were
    1.40
     are
    1.27
     weren
    1.16
     WERE
    1.13
    were
    1.12
     ARE
    1.02
     aren
    0.97
    Were
    0.96
     Were
    0.91
    are
    0.91
    Activations Density 4.196%

    No Known Activations