© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8166
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C and PHP code

    oai_token-act-pair · gemini-2.0-flash

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     GenerationType
    -0.63
    WebVitals
    -0.60
    +#+#
    -0.57
    Geplaatst
    -0.55
     समीक्षाओं
    -0.54
    Portail
    -0.53
    MemoryWarning
    -0.52
    AndEndTag
    -0.52
     AssemblyCulture
    -0.50
    enderror
    -0.50
    POSITIVE LOGITS
    MergeFrom
    0.61
    loroethene
    0.58
    dafx
    0.55
     mortes
    0.52
     untere
    0.50
     iprot
    0.50
     anteriore
    0.49
     pourtant
    0.48
    óz
    0.48
     Beren
    0.48
    Activations Density 1.193%

    No Known Activations