© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4072
    Prev
    Next
    INDEX
    Explanations

    references to authorship, ownership, and belonging through possessive pronouns/determiners and verbs of creation.

    oai_token-act-pair · gemini-2.0-flash

    his

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WaitGroup
    -0.59
    <bos>
    -0.56
    Their
    -0.53
    their
    -0.52
     Their
    -0.52
    脚注の使い方
    -0.50
     onCancelled
    -0.49
     their
    -0.48
     lenker
    -0.48
     Possibility
    -0.48
    POSITIVE LOGITS
     wife
    0.82
    saraba
    0.68
     daughter
    0.68
     Efq
    0.64
     son
    0.62
     own
    0.59
     father
    0.59
     mother
    0.57
     husband
    0.57
     usual
    0.56
    Activations Density 7.890%

    No Known Activations