© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8710
    Prev
    Next
    INDEX
    Explanations

    the word "return" and its variants ("returns", "returned", "returning")

    oai_token-act-pair · gemini-2.0-flash

    return

    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
    ValueStyle
    -0.53
    getMenuInflater
    -0.45
    ográficos
    -0.45
    InjectAttribute
    -0.44
    ual
    -0.44
    uesia
    -0.44
    razine
    -0.42
     meeting
    -0.42
    EDEFAULT
    -0.42
     tratta
    -0.42
    POSITIVE LOGITS
     returns
    1.64
     Returns
    1.63
     Return
    1.58
     return
    1.56
    Returns
    1.52
    Return
    1.48
    returns
    1.44
     RETURN
    1.37
    return
    1.35
     RETURNS
    1.32
    Activations Density 0.068%

    No Known Activations