© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9981
    Prev
    Next
    INDEX
    Explanations

    abbreviations or shortened forms of words, especially those ending in "pt" or "ct".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    MemoryWarning
    -0.86
    XmlAccessorType
    -0.72
     kasarigan
    -0.71
    PerformLayout
    -0.70
    parsedMessage
    -0.70
    writeField
    -0.69
    RegistryLite
    -0.67
    Personendaten
    -0.66
    EndInit
    -0.65
    Péri
    -0.64
    POSITIVE LOGITS
     except
    0.58
    FlatStyle
    0.52
    Except
    0.50
    EXCEPT
    0.50
    cepted
    0.48
    except
    0.47
     excep
    0.47
     Except
    0.47
    Minus
    0.46
    ත්
    0.46
    Activations Density 0.642%

    No Known Activations