© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 525
    Prev
    Next
    INDEX
    Explanations

    code snippets across multiple programming languages

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CodeAttribute
    -0.49
     praktijk
    -0.48
     aikaa
    -0.47
     picioare
    -0.46
     bestaande
    -0.46
     löytyy
    -0.45
     poches
    -0.45
     scurt
    -0.45
     Notwendigkeit
    -0.45
    Géographie
    -0.44
    POSITIVE LOGITS
    #+#
    0.71
    ExecuteReader
    0.56
    PreferredItem
    0.56
    '])
    0.55
    ysty
    0.54
    Personendaten
    0.53
    Partitions
    0.53
    :+:
    0.52
    ξη
    0.52
    issi
    0.51
    Activations Density 3.857%

    No Known Activations