© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5981
    Prev
    Next
    INDEX
    Explanations

    the verb "came" and similar, especially in past tense

    oai_token-act-pair · gemini-2.0-flash

    come

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     came
    -2.33
     comes
    -2.06
    came
    -1.99
     come
    -1.95
    Came
    -1.85
     Came
    -1.70
     Come
    -1.68
     Comes
    -1.66
    Come
    -1.66
    comes
    -1.66
    POSITIVE LOGITS
     strconv
    0.58
     faute
    0.56
     LUMP
    0.56
     imageNamed
    0.53
    懋
    0.52
    OPSIS
    0.51
    ricle
    0.51
    lified
    0.50
    illus
    0.49
     plomb
    0.49
    Activations Density 1.367%

    No Known Activations