© 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. 13506
    Prev
    Next
    INDEX
    Explanations

    the word "at" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    legal or historical contexts

    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
     المعيارى
    -1.05
    
    -0.98
    ScopeManager
    -0.91
    <?
    -0.82
     InputDecoration
    -0.79
     ब्रेकडाउन
    -0.78
    PhysRevD
    -0.76
     Réponses
    -0.76
    </thead>
    -0.74
     HomeComponent
    -0.73
    POSITIVE LOGITS
    ubility
    0.35
     купе
    0.35
    xsi
    0.35
     stano
    0.34
     定
    0.34
     stated
    0.33
    colnshire
    0.33
    opard
    0.33
     dispu
    0.32
     DialogInterface
    0.32
    Activations Density 0.780%

    No Known Activations