© 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. 3617
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    move

    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
    NameInMap
    -0.56
     tạp
    -0.54
     "'");
    -0.47
     Daß
    -0.46
    Parade
    -0.45
     Ausbau
    -0.44
     zachod
    -0.44
     cadrul
    -0.43
    setLevel
    -0.43
    ！");
    -0.43
    POSITIVE LOGITS
     moved
    2.08
     Moved
    1.79
    moved
    1.66
    Moved
    1.64
     move
    1.61
     moves
    1.49
     Move
    1.47
    move
    1.46
     MOVE
    1.38
    Move
    1.37
    Activations Density 1.865%

    No Known Activations