© 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. 5446
    Prev
    Next
    INDEX
    Explanations

    instances of "return" or "returning" and related concepts.

    oai_token-act-pair · gemini-2.0-flash

    return

    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
     return
    -2.91
     returned
    -2.66
     returning
    -2.56
     returns
    -2.53
     Return
    -2.52
    return
    -2.36
    Return
    -2.31
     Returning
    -2.30
     RETURN
    -2.30
    Returning
    -2.19
    POSITIVE LOGITS
     ExecuteAsync
    0.77
    pexpr
    0.69
    DockStyle
    0.67
    TintMode
    0.67
    DllImport
    0.61
    WriteAttribute
    0.60
    Parcelize
    0.57
     AssemblyCulture
    0.57
    styleable
    0.56
     ProtoMessage
    0.55
    Activations Density 1.497%

    No Known Activations