© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5063
    Prev
    Next
    INDEX
    Explanations

    a mix of legal language, religious references, and pronoun usage, especially words like "He," "His," and "Allah."

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     She
    -1.20
     He
    -1.19
     We
    -1.16
     They
    -0.80
     WE
    -0.71
     You
    -0.71
    She
    -0.69
    We
    -0.68
    He
    -0.60
     Мы
    -0.49
    POSITIVE LOGITS
     His
    1.34
    His
    1.17
     Himself
    1.06
     Him
    1.05
     Their
    0.98
    Her
    0.95
     Her
    0.93
    Him
    0.93
     Own
    0.91
     HIS
    0.88
    Activations Density 7.010%

    No Known Activations