© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4939
    Prev
    Next
    INDEX
    Explanations

    language pertaining to ecological studies, specifically bird habitats

    oai_token-act-pair · gemini-2.0-flash

    hunt

    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
     arşivlendi
    -0.77
    buttonBar
    -0.77
    rungsseite
    -0.75
    SharedCtor
    -0.75
    featureID
    -0.75
    extAlignment
    -0.75
     betweenstory
    -0.75
     Administrativna
    -0.73
     wireType
    -0.72
    ChildScrollView
    -0.71
    POSITIVE LOGITS
     hunt
    0.53
     feeding
    0.49
     hunting
    0.48
     feed
    0.46
    aring
    0.43
     nourrir
    0.43
     pêche
    0.40
     Hunt
    0.40
     fed
    0.40
     oeil
    0.39
    Activations Density 1.912%

    No Known Activations