© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14047
    Prev
    Next
    INDEX
    Explanations

    words connected to religious feelings and actions

    oai_token-act-pair · gemini-2.0-flash

    religious life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     fallu
    -0.65
    
    -0.58
    Hentet
    -0.57
     وتسجيلات
    -0.54
    wiches
    -0.52
    adaptiveStyles
    -0.52
    PreInfinity
    -0.52
    脚注の使い方
    -0.52
     Exacts
    -0.51
    yakarta
    -0.50
    POSITIVE LOGITS
    XmlAccessorType
    0.79
     '\\;'
    0.67
     GenerationType
    0.63
    unknownFields
    0.52
     Hartman
    0.49
    下手
    0.48
    })]
    0.47
    Rptr
    0.47
     protoimpl
    0.46
    ".$_
    0.46
    Activations Density 2.753%

    No Known Activations