© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3590
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to religious worship rituals

    oai_token-act-pair · gemini-2.0-flash

    religious/cultural 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_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
    ండ
    -0.41
     mempel
    -0.38
    eacute
    -0.38
     Neighbor
    -0.38
    le
    -0.36
     []:
    -0.36
    Elles
    -0.35
    è
    -0.35
    readAll
    -0.35
    ora
    -0.35
    POSITIVE LOGITS
    styleType
    0.71
     Normdatei
    0.69
    AddTagHelper
    0.69
    idopsis
    0.68
     estekak
    0.68
     الحره
    0.67
    kloped
    0.67
    asthan
    0.66
     tartalomajánló
    0.65
    claimer
    0.63
    Activations Density 3.739%

    No Known Activations