© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6362
    Prev
    Next
    INDEX
    Explanations

    technical writing discussing efficiency

    oai_token-act-pair · gemini-2.0-flash

    surface

    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
     wireType
    -0.68
    WriteBarrier
    -0.58
    IGraphics
    -0.56
     ilmo
    -0.54
     uſed
    -0.54
     jsPsych
    -0.54
    ſelves
    -0.53
     poffible
    -0.53
    StoryboardSegue
    -0.52
     ſhould
    -0.52
    POSITIVE LOGITS
     surface
    2.28
    surface
    1.96
     Surface
    1.92
    Surface
    1.76
     SURFACE
    1.74
    SURFACE
    1.55
     superficie
    1.48
     surfaces
    1.46
    urface
    1.41
     Surfaces
    1.26
    Activations Density 2.489%

    No Known Activations