© 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. 9325
    Prev
    Next
    INDEX
    Explanations

    first person subjective pronouns and verbs plus related qualifiers

    oai_token-act-pair · gemini-2.0-flash

    unique identifier tokens or names

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

    personal anecdotes/blog posts

    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
    ρίες
    -0.59
     تانيه
    -0.57
    estay
    -0.53
    <_>
    -0.52
     Col
    -0.51
    chließend
    -0.51
    BeginInit
    -0.50
     dne
    -0.50
     daly
    -0.49
    ponses
    -0.48
    POSITIVE LOGITS
    Spoljašnje
    0.61
    WithIOException
    0.54
    oredCriteria
    0.51
     Paglinawan
    0.49
     '{@
    0.48
     a
    0.48
    ThroughAttribute
    0.48
    исленность
    0.47
     Roskov
    0.47
    thora
    0.47
    Activations Density 0.724%

    No Known Activations