© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6603
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to the act of moving, paths/trails, and place/personal names

    oai_token-act-pair · gemini-2.0-flash

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    enderror
    -0.52
    Datuak
    -0.52
     Implant
    -0.51
     getAge
    -0.50
     Pool
    -0.49
     Pools
    -0.48
     setName
    -0.47
    indd
    -0.47
     coscienza
    -0.47
     fuzz
    -0.47
    POSITIVE LOGITS
     walk
    1.80
     walking
    1.68
    walk
    1.66
     walks
    1.65
     walked
    1.60
     WALK
    1.59
     Walk
    1.56
    Walk
    1.52
    Walking
    1.52
    walks
    1.51
    Activations Density 0.620%

    No Known Activations