© 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. 7369
    Prev
    Next
    INDEX
    Explanations

    references to government or leadership

    oai_token-act-pair · gemini-2.0-flash

    current events

    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
     فريبيس
    -0.87
    ConstraintMaker
    -0.65
     AssemblyCulture
    -0.62
    BufferException
    -0.58
    abestanden
    -0.57
    tonode
    -0.57
    thâu
    -0.57
     utafitiHapana
    -0.56
     mergeFrom
    -0.56
    LookAnd
    -0.55
    POSITIVE LOGITS
    imgur
    0.52
    pae
    0.45
     ordf
    0.44
     formally
    0.43
     resmi
    0.42
     pass
    0.42
    providedIn
    0.42
     Hage
    0.42
    })));
    0.41
    Al
    0.41
    Activations Density 1.727%

    No Known Activations