© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12231
    Prev
    Next
    INDEX
    Explanations

    the phrase "so that" or other phrases that show cause and effect

    oai_token-act-pair · gemini-2.0-flash

    repetitive use of the word 'so'

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

    so

    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
     oprot
    -0.51
     sposob
    -0.49
    消
    -0.48
    Viited
    -0.44
     able
    -0.42
    GrantedAuthority
    -0.42
    MockMvc
    -0.42
    ագրություններ
    -0.42
    AccessFile
    -0.41
    databind
    -0.41
    POSITIVE LOGITS
     that
    1.33
     they
    0.67
     we
    0.67
     eset
    0.66
    that
    0.66
     contextLoads
    0.65
    uxxxx
    0.62
     protoimpl
    0.61
    makeConstraints
    0.61
    <bos>
    0.59
    Activations Density 1.469%

    No Known Activations