© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8301
    Prev
    Next
    INDEX
    Explanations

    mentions of goals, plans, and key areas

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Waray
    -0.54
    Cyfeiriadau
    -0.54
    \{\\
    -0.52
     nakalista
    -0.52
     Normdatei
    -0.52
    adaptiveStyles
    -0.51
    ]-->
    -0.49
    klein
    -0.48
    Personendaten
    -0.47
    UnknownFields
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.72
     direction
    0.66
     axis
    0.66
     åt
    0.65
     directions
    0.63
     Concentrate
    0.62
     concentrates
    0.62
     areas
    0.62
    的方向
    0.59
    direction
    0.59
    Activations Density 1.705%

    No Known Activations