© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3032
    Prev
    Next
    INDEX
    Explanations

    the word "come" along with related words about cases, mail, books and wanting.

    oai_token-act-pair · gemini-2.0-flash

    various forms of the word "come"

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

    coming or back

    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
    styleable
    -0.63
    IntoConstraints
    -0.63
     Unavailable
    -0.58
     Coming
    -0.57
    AddTagHelper
    -0.57
    HasForeignKey
    -0.55
    undum
    -0.54
    onnaissance
    -0.53
    WithIOException
    -0.52
    entieth
    -0.52
    POSITIVE LOGITS
     الحره
    0.72
    RegressionTest
    0.59
     back
    0.58
     into
    0.57
    __()
    0.50
    .*")]
    0.50
     发表于
    0.49
     GestureDetector
    0.49
    AndEndTag
    0.49
     cyclisme
    0.48
    Activations Density 1.835%

    No Known Activations