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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11270
    Prev
    Next
    INDEX
    Explanations

    uses of "would like", "you" followed by would, and present tense verbs related to appearance

    oai_token-act-pair · gemini-2.0-flash

    similarity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    protoimpl
    -0.63
    хьтан
    -0.57
    IUrlHelper
    -0.57
    بوابة
    -0.56
    ParseTree
    -0.54
    rawDesc
    -0.54
    Demografía
    -0.53
    ampilan
    -0.51
    ußer
    -0.50
    SharedCtor
    -0.50
    POSITIVE LOGITS
     similar
    1.04
    Similar
    0.91
     Similar
    0.91
    similar
    0.82
     podob
    0.76
     such
    0.73
     semelhante
    0.69
     SIMILAR
    0.67
     similarity
    0.66
     similaire
    0.65
    Activations Density 0.724%

    No Known Activations