© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14324
    Prev
    Next
    INDEX
    Explanations

    instances of someone describing or considering themself to be something

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    uxxxx
    -0.82
    ########.
    -0.71
    HasForeignKey
    -0.69
     beginnetje
    -0.68
    expandindo
    -0.66
     nahilalakip
    -0.58
    دانشنامهٔ
    -0.57
     виправивши
    -0.57
    रीदारी
    -0.56
    ToEnd
    -0.56
    POSITIVE LOGITS
     considered
    0.66
     considerato
    0.66
    ManagedBean
    0.65
    ItemBackground
    0.58
    considered
    0.57
     consider
    0.54
     consideran
    0.53
    idered
    0.53
     considerado
    0.52
     classed
    0.52
    Activations Density 0.803%

    No Known Activations