© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4495
    Prev
    Next
    INDEX
    Explanations

    sections of text that compare two different people, potentially in a competitive or contrasting manner.

    oai_token-act-pair · gemini-2.0-flash

    words related to self-reference and identity

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

    that

    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
    siger
    -0.44
    統
    -0.44
    utet
    -0.43
     consultez
    -0.42
     hào
    -0.41
     endforeach
    -0.40
    avigation
    -0.40
     disposition
    -0.39
    Copyright
    -0.39
     ['./
    -0.38
    POSITIVE LOGITS
    jooq
    0.72
    mặt
    0.71
    rictive
    0.69
     itſelf
    0.68
    TypedDataSet
    0.68
    MemoryWarning
    0.68
     للمعارف
    0.68
     myſelf
    0.67
     beginnetje
    0.67
    IsMutable
    0.65
    Activations Density 0.151%

    No Known Activations