© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11391
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people and words related to negative experiences

    oai_token-act-pair · gemini-2.0-flash

    him

    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
     him
    -1.59
     Him
    -1.31
    him
    -1.21
    Him
    -1.13
     her
    -1.02
     HIM
    -0.88
     herself
    -0.80
    HIM
    -0.77
    herself
    -0.69
     ihn
    -0.68
    POSITIVE LOGITS
    ValueGenerated
    0.63
    DeleteBehavior
    0.59
    IsContent
    0.59
    曖昧さ回避
    0.58
     CreateTagHelper
    0.58
    ']))
    0.57
     فريبيس
    0.57
     contextLoads
    0.57
     ―――――
    0.57
    AlterField
    0.56
    Activations Density 2.122%

    No Known Activations