© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9760
    Prev
    Next
    INDEX
    Explanations

    religious text, specifically mentioning Allah/God and related concepts.

    oai_token-act-pair · gemini-2.0-flash

    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
     His
    -1.20
     Him
    -1.12
    His
    -1.11
     Himself
    -0.98
    Him
    -0.95
    Her
    -0.89
     Own
    -0.85
     Его
    -0.80
     HIS
    -0.80
     HIM
    -0.79
    POSITIVE LOGITS
     We
    1.40
     He
    1.20
     She
    1.14
     You
    0.95
     They
    0.92
     WE
    0.82
    We
    0.72
     Мы
    0.63
     There
    0.57
     Thou
    0.57
    Activations Density 7.312%

    No Known Activations