© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12968
    Prev
    Next
    INDEX
    Explanations

    the word "earth" and its derivatives

    oai_token-act-pair · gemini-2.0-flash

    Earth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    nativeElement
    -0.70
     fermés
    -0.68
    loroethene
    -0.67
    LookAnd
    -0.65
     répon
    -0.63
    DeleteBehavior
    -0.63
     étoient
    -0.60
    ształ
    -0.59
     SPIE
    -0.59
     déclar
    -0.58
    POSITIVE LOGITS
     care
    0.49
     समीक्षाएं
    0.48
     artific
    0.46
    下一篇
    0.45
    rics
    0.45
     Cot
    0.44
    care
    0.44
     Ar
    0.43
    chkin
    0.43
    loga
    0.42
    Activations Density 1.038%

    No Known Activations