© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2579
    Prev
    Next
    INDEX
    Explanations

    religious language referencing Allah, punishment and subservience

    oai_token-act-pair · gemini-2.0-flash

    Religious/historical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    IntoConstraints
    -0.86
    AndEndTag
    -0.81
     InputDecoration
    -0.80
     AssemblyTitle
    -0.77
     snippetHide
    -0.76
    MethodManager
    -0.71
     StringTokenizer
    -0.66
    Clik
    -0.66
     onData
    -0.66
    
    -0.66
    POSITIVE LOGITS
     ***!
    0.48
     Belie
    0.47
    pala
    0.46
    IFEST
    0.45
    slave
    0.44
    Ciao
    0.44
     Religions
    0.42
    PASSED
    0.42
     romanti
    0.42
     adoration
    0.42
    Activations Density 2.850%

    No Known Activations