© 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. 8899
    Prev
    Next
    INDEX
    Explanations

    the phrase "let's" (including capitalization variants and the variant "let me")

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "let"

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

    let

    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
     let
    -0.48
     much
    -0.46
    rophobic
    -0.44
    let
    -0.44
    cloudf
    -0.43
     mucho
    -0.42
     uchun
    -0.41
     Much
    -0.41
    sieren
    -0.40
    createElement
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.87
    IUrlHelper
    0.73
    ReusableCell
    0.69
    TemporalType
    0.66
    protoimpl
    0.66
    ApiModelProperty
    0.65
    IsContent
    0.64
     protoimpl
    0.63
    存于互联网档案馆
    0.63
    ?>">
    0.60
    Activations Density 0.378%

    No Known Activations