© 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. 5589
    Prev
    Next
    INDEX
    Explanations

    words and phrases that represent movement or an inclination towards something

    oai_token-act-pair · gemini-2.0-flash

    Research and trends

    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
     direction
    -1.26
     Direction
    -1.23
    direction
    -1.20
     DIRECTION
    -1.17
     Forward
    -1.16
    Forward
    -1.11
     directions
    -1.11
     FORWARD
    -1.09
    forward
    -1.07
    Direction
    -1.07
    POSITIVE LOGITS
    word
    0.54
    Word
    0.46
    wd
    0.45
    wad
    0.42
     tow
    0.41
    ReusableCell
    0.41
    WD
    0.39
    arium
    0.38
     word
    0.38
     Ababa
    0.37
    Activations Density 1.294%

    No Known Activations