© 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. 7182
    Prev
    Next
    INDEX
    Explanations

    motivational or inspirational phrases

    oai_token-act-pair · gemini-2.0-flash

    overcoming adversity

    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
    enterOuterAlt
    -0.88
    الإنجليزية
    -0.74
    DotNetBar
    -0.71
     typelib
    -0.66
    WebControls
    -0.65
    ScopeManager
    -0.64
    itinéraire
    -0.62
    WithIOException
    -0.59
    ंदीखरीदारी
    -0.58
    UnusedPrivate
    -0.58
    POSITIVE LOGITS
     MutableLiveData
    0.60
    <bos>
    0.46
     FOC
    0.46
    Pur
    0.45
     reach
    0.45
    });*/
    0.44
     surround
    0.44
     Pur
    0.44
    ResourceType
    0.42
     تضيفلها
    0.41
    Activations Density 1.518%

    No Known Activations