© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3015
    Prev
    Next
    INDEX
    Explanations

    words related to magic, witchcraft, the supernatural, or stories and tales of yore.

    oai_token-act-pair · gemini-2.0-flash

    fantasy stories

    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
    Negative Logits
     forState
    -0.68
    WebElementEntity
    -0.68
    Бахар
    -0.62
    }))
    -0.59
    Personendaten
    -0.58
    ChildIndex
    -0.57
    KommentareTeilen
    -0.57
     Chriftian
    -0.57
     متعلقه
    -0.57
    ?»
    -0.57
    POSITIVE LOGITS
    ACHE
    0.54
     consume
    0.52
    omeness
    0.51
     protoimpl
    0.51
     consumes
    0.50
     ModelExpression
    0.49
    consume
    0.48
     Consume
    0.47
    Consume
    0.47
     Steal
    0.47
    Activations Density 4.421%

    No Known Activations