© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11754
    Prev
    Next
    INDEX
    Explanations

    text discussing religion

    oai_token-act-pair · gemini-2.0-flash

    Religion and faith

    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
    WebVitals
    -0.66
     kasarigan
    -0.57
    enderror
    -0.56
    astify
    -0.53
     Guanajuato
    -0.49
    LookAnd
    -0.49
    Jeografia
    -0.48
     Roskov
    -0.48
     ControllerBase
    -0.46
    펴
    -0.46
    POSITIVE LOGITS
     تانيه
    0.56
    chọn
    0.56
    ADORES
    0.55
    BagLayout
    0.52
    enumi
    0.50
     Paterson
    0.50
    entrySet
    0.50
     Semi
    0.48
    koe
    0.48
    Semi
    0.48
    Activations Density 7.202%

    No Known Activations