© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13701
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to achieving a goal

    oai_token-act-pair · gemini-2.0-flash

    meet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    SpringRunner
    -0.67
    Gambas
    -0.60
    StoryboardSegue
    -0.60
    ніципалі
    -0.58
    Implementation
    -0.58
    DeleteBehavior
    -0.58
     transfieras
    -0.57
    PathVariable
    -0.57
     Савезне
    -0.57
     Geophys
    -0.56
    POSITIVE LOGITS
     met
    1.38
     meet
    1.33
     meeting
    1.28
    meet
    1.24
     meets
    1.24
     Meet
    1.20
     reach
    1.18
    Meet
    1.16
     reached
    1.15
    Met
    1.13
    Activations Density 4.000%

    No Known Activations